@article{14041,
  abstract     = {Tissue morphogenesis and patterning during development involve the segregation of cell types. Segregation is driven by differential tissue surface tensions generated by cell types through controlling cell-cell contact formation by regulating adhesion and actomyosin contractility-based cellular cortical tensions. We use vertebrate tissue cell types and zebrafish germ layer progenitors as in vitro models of 3-dimensional heterotypic segregation and developed a quantitative analysis of their dynamics based on 3D time-lapse microscopy. We show that general inhibition of actomyosin contractility by the Rho kinase inhibitor Y27632 delays segregation. Cell type-specific inhibition of non-muscle myosin2 activity by overexpression of myosin assembly inhibitor S100A4 reduces tissue surface tension, manifested in decreased compaction during aggregation and inverted geometry observed during segregation. The same is observed when we express a constitutively active Rho kinase isoform to ubiquitously keep actomyosin contractility high at cell-cell and cell-medium interfaces and thus overriding the interface-specific regulation of cortical tensions. Tissue surface tension regulation can become an effective tool in tissue engineering.},
  author       = {Méhes, Elod and Mones, Enys and Varga, Máté and Zsigmond, Áron and Biri-Kovács, Beáta and Nyitray, László and Barone, Vanessa and Krens, Gabriel and Heisenberg, Carl-Philipp J and Vicsek, Tamás},
  issn         = {2399-3642},
  journal      = {Communications Biology},
  publisher    = {Springer Nature},
  title        = {{3D cell segregation geometry and dynamics are governed by tissue surface tension regulation}},
  doi          = {10.1038/s42003-023-05181-7},
  volume       = {6},
  year         = {2023},
}

@article{14042,
  abstract     = {Long-time and large-data existence of weak solutions for initial- and boundary-value problems concerning three-dimensional flows of incompressible fluids is nowadays available not only for Navier–Stokes fluids but also for various fluid models where the relation between the Cauchy stress tensor and the symmetric part of the velocity gradient is nonlinear. The majority of such studies however concerns models where such a dependence is explicit (the stress is a function of the velocity gradient), which makes the class of studied models unduly restrictive. The same concerns boundary conditions, or more precisely the slipping mechanisms on the boundary, where the no-slip is still the most preferred condition considered in the literature. Our main objective is to develop a robust mathematical theory for unsteady internal flows of implicitly constituted incompressible fluids with implicit relations between the tangential projections of the velocity and the normal traction on the boundary. The theory covers numerous rheological models used in chemistry, biorheology, polymer and food industry as well as in geomechanics. It also includes, as special cases, nonlinear slip as well as stick–slip boundary conditions. Unlike earlier studies, the conditions characterizing admissible classes of constitutive equations are expressed by means of tools of elementary calculus. In addition, a fully constructive proof (approximation scheme) is incorporated. Finally, we focus on the question of uniqueness of such weak solutions.},
  author       = {Bulíček, Miroslav and Málek, Josef and Maringová, Erika},
  issn         = {1422-6952},
  journal      = {Journal of Mathematical Fluid Mechanics},
  number       = {3},
  publisher    = {Springer Nature},
  title        = {{On unsteady internal flows of incompressible fluids characterized by implicit constitutive equations in the bulk and on the boundary}},
  doi          = {10.1007/s00021-023-00803-w},
  volume       = {25},
  year         = {2023},
}

@article{14043,
  abstract     = {Over the last two decades, a significant line of work in theoretical algorithms has made progress in solving linear systems of the form Lx=b, where L is the Laplacian matrix of a weighted graph with weights w(i,j)>0 on the edges. The solution x of the linear system can be interpreted as the potentials of an electrical flow in which the resistance on edge (i, j) is 1/w(i, j). Kelner et al. (in: Proceedings of the 45th Annual ACM Symposium on the Theory of Computing, pp 911–920, 2013. https://doi.org/10.1145/2488608.2488724) give a combinatorial, near-linear time algorithm that maintains the Kirchoff Current Law, and gradually enforces the Kirchoff Potential Law by updating flows around cycles (cycle toggling). In this paper, we consider a dual version of the algorithm that maintains the Kirchoff Potential Law, and gradually enforces the Kirchoff Current Law by cut toggling: each iteration updates all potentials on one side of a fundamental cut of a spanning tree by the same amount. We prove that this dual algorithm also runs in a near-linear number of iterations. We show, however, that if we abstract cut toggling as a natural data structure problem, this problem can be reduced to the online vector–matrix-vector problem, which has been conjectured to be difficult for dynamic algorithms (Henzinger et al., in: Proceedings of the 47th Annual ACM Symposium on the Theory of Computing, pp 21–30, 2015. https://doi.org/10.1145/2746539.2746609). The conjecture implies that the data structure does not have an O(n1−ϵ) time algorithm for any ϵ>0, and thus a straightforward implementation of the cut-toggling algorithm requires essentially linear time per iteration. To circumvent the lower bound, we batch update steps, and perform them simultaneously instead of sequentially. An appropriate choice of batching leads to an O˜(m1.5) time cut-toggling algorithm for solving Laplacian systems. Furthermore, we show that if we sparsify the graph and call our algorithm recursively on the Laplacian system implied by batching and sparsifying, we can reduce the running time to O(m1+ϵ) for any ϵ>0. Thus, the dual cut-toggling algorithm can achieve (almost) the same running time as its primal cycle-toggling counterpart.},
  author       = {Henzinger, Monika H and Jin, Billy and Peng, Richard and Williamson, David P.},
  issn         = {1432-0541},
  journal      = {Algorithmica},
  pages        = {2680--3716},
  publisher    = {Springer Nature},
  title        = {{A combinatorial cut-toggling algorithm for solving Laplacian linear systems}},
  doi          = {10.1007/s00453-023-01154-8},
  volume       = {85},
  year         = {2023},
}

@phdthesis{14058,
  abstract     = {Females and males across species are subject to divergent selective pressures arising
from di↵erent reproductive interests and ecological niches. This often translates into a
intricate array of sex-specific natural and sexual selection on traits that have a shared
genetic basis between both sexes, causing a genetic sexual conflict. The resolution of
this conflict mostly relies on the evolution of sex-specific expression of the shared genes,
leading to phenotypic sexual dimorphism. Such sex-specific gene expression is thought
to evolve via modifications of the genetic networks ultimately linked to sex-determining
transcription factors. Although much empirical and theoretical evidence supports this
standard picture of the molecular basis of sexual conflict resolution, there still are a
few open questions regarding the complex array of selective forces driving phenotypic
di↵erentiation between the sexes, as well as the molecular mechanisms underlying sexspecific adaptation. I address some of these open questions in my PhD thesis.
First, how do patterns of phenotypic sexual dimorphism vary within populations,
as a response to the temporal and spatial changes in sex-specific selective forces? To
tackle this question, I analyze the patterns of sex-specific phenotypic variation along
three life stages and across populations spanning the whole geographical range of Rumex
hastatulus, a wind-pollinated angiosperm, in the first Chapter of the thesis.
Second, how do gene expression patterns lead to phenotypic dimorphism, and what
are the molecular mechanisms underlying the observed transcriptomic variation? I
address this question by examining the sex- and tissue-specific expression variation in
newly-generated datasets of sex-specific expression in heads and gonads of Drosophila
melanogaster. I additionally used two complementary approaches for the study of the
genetic basis of sex di↵erences in gene expression in the second and third Chapters of
the thesis.
Third, how does intersex correlation, thought to be one of the main aspects constraining the ability for the two sexes to decouple, interact with the evolution of sexual
dimorphism? I develop models of sex-specific stabilizing selection, mutation and drift
to formalize common intuition regarding the patterns of covariation between intersex
correlation and sexual dimorphism in the fourth Chapter of the thesis.
Alltogether, the work described in this PhD thesis provides useful insights into the
links between genetic, transcriptomic and phenotypic layers of sex-specific variation,
and contributes to our general understanding of the dynamics of sexual dimorphism
evolution.},
  author       = {Puixeu Sala, Gemma},
  isbn         = {978-3-99078-035-0},
  issn         = {2663-337X},
  pages        = {230},
  publisher    = {Institute of Science and Technology Austria},
  title        = {{The molecular basis of sexual dimorphism: Experimental and theoretical characterization of phenotypic, transcriptomic and genetic patterns of sex-specific adaptation}},
  doi          = {10.15479/at:ista:14058},
  year         = {2023},
}

@inproceedings{14076,
  abstract     = {Hyperproperties are properties that relate multiple execution traces. Previous work on monitoring hyperproperties focused on synchronous hyperproperties, usually specified in HyperLTL. When monitoring synchronous hyperproperties, all traces are assumed to proceed at the same speed. We introduce (multi-trace) prefix transducers and show how to use them for monitoring synchronous as well as, for the first time, asynchronous hyperproperties. Prefix transducers map multiple input traces into one or more output traces by incrementally matching prefixes of the input traces against expressions similar to regular expressions. The prefixes of different traces which are consumed by a single matching step of the monitor may have different lengths. The deterministic and executable nature of prefix transducers makes them more suitable as an intermediate formalism for runtime verification than logical specifications, which tend to be highly non-deterministic, especially in the case of asynchronous hyperproperties. We report on a set of experiments about monitoring asynchronous version of observational determinism.},
  author       = {Chalupa, Marek and Henzinger, Thomas A},
  booktitle    = {23nd International Conference on Runtime Verification},
  isbn         = {978-3-031-44266-7},
  location     = {Thessaloniki, Greek},
  pages        = {168--190},
  publisher    = {Springer Nature},
  title        = {{Monitoring hyperproperties with prefix transducers}},
  doi          = {10.1007/978-3-031-44267-4_9},
  volume       = {14245},
  year         = {2023},
}

@article{14077,
  abstract     = {The regulatory architecture of gene expression is known to differ substantially between sexes in Drosophila, but most studies performed
so far used whole-body data and only single crosses, which may have limited their scope to detect patterns that are robust across tissues
and biological replicates. Here, we use allele-specific gene expression of parental and reciprocal hybrid crosses between 6 Drosophila
melanogaster inbred lines to quantify cis- and trans-regulatory variation in heads and gonads of both sexes separately across 3 replicate
crosses. Our results suggest that female and male heads, as well as ovaries, have a similar regulatory architecture. On the other hand,
testes display more and substantially different cis-regulatory effects, suggesting that sex differences in the regulatory architecture that
have been previously observed may largely derive from testis-specific effects. We also examine the difference in cis-regulatory variation
of genes across different levels of sex bias in gonads and heads. Consistent with the idea that intersex correlations constrain expression
and can lead to sexual antagonism, we find more cis variation in unbiased and moderately biased genes in heads. In ovaries, reduced cis
variation is observed for male-biased genes, suggesting that cis variants acting on these genes in males do not lead to changes in ovary
expression. Finally, we examine the dominance patterns of gene expression and find that sex- and tissue-specific patterns of inheritance
as well as trans-regulatory variation are highly variable across biological crosses, although these were performed in highly controlled
experimental conditions. This highlights the importance of using various genetic backgrounds to infer generalizable patterns.},
  author       = {Puixeu Sala, Gemma and Macon, Ariana and Vicoso, Beatriz},
  issn         = {2160-1836},
  journal      = {G3: Genes, Genomes, Genetics},
  keywords     = {Genetics (clinical), Genetics, Molecular Biology},
  number       = {8},
  publisher    = {Oxford University Press},
  title        = {{Sex-specific estimation of cis and trans regulation of gene expression in heads and gonads of Drosophila melanogaster}},
  doi          = {10.1093/g3journal/jkad121},
  volume       = {13},
  year         = {2023},
}

@article{14080,
  abstract     = {Extracellular signal-regulated kinase (ERK) has been recognized as a critical regulator in various physiological and pathological processes. Extensive research has elucidated the signaling mechanisms governing ERK activation via biochemical regulations with upstream molecules, particularly receptor tyrosine kinases (RTKs). However, recent advances have highlighted the role of mechanical forces in activating the RTK–ERK signaling pathways, thereby opening new avenues of research into mechanochemical interplay in multicellular tissues. Here, we review the force-induced ERK activation in cells and propose possible mechanosensing mechanisms underlying the mechanoresponsive ERK activation. We conclude that mechanical forces are not merely passive factors shaping cells and tissues but also active regulators of cellular signaling pathways controlling collective cell behaviors.},
  author       = {Hirashima, Tsuyoshi and Hino, Naoya and Aoki, Kazuhiro and Matsuda, Michiyuki},
  issn         = {1879-0410},
  journal      = {Current Opinion in Cell Biology},
  number       = {10},
  publisher    = {Elsevier},
  title        = {{Stretching the limits of extracellular signal-related kinase (ERK) signaling — Cell mechanosensing to ERK activation}},
  doi          = {10.1016/j.ceb.2023.102217},
  volume       = {84},
  year         = {2023},
}

@article{14082,
  abstract     = {Epithelial barrier function is commonly analyzed using transepithelial electrical resistance, which measures ion flux across a monolayer, or by adding traceable macromolecules and monitoring their passage across the monolayer. Although these methods measure changes in global barrier function, they lack the sensitivity needed to detect local or transient barrier breaches, and they do not reveal the location of barrier leaks. Therefore, we previously developed a method that we named the zinc-based ultrasensitive microscopic barrier assay (ZnUMBA), which overcomes these limitations, allowing for detection of local tight junction leaks with high spatiotemporal resolution. Here, we present expanded applications for ZnUMBA. ZnUMBA can be used in Xenopus embryos to measure the dynamics of barrier restoration and actin accumulation following laser injury. ZnUMBA can also be effectively utilized in developing zebrafish embryos as well as cultured monolayers of Madin–Darby canine kidney (MDCK) II epithelial cells. ZnUMBA is a powerful and flexible method that, with minimal optimization, can be applied to multiple systems to measure dynamic changes in barrier function with spatiotemporal precision.},
  author       = {Higashi, Tomohito and Stephenson, Rachel E. and Schwayer, Cornelia and Huljev, Karla and Higashi, Atsuko Y. and Heisenberg, Carl-Philipp J and Chiba, Hideki and Miller, Ann L.},
  issn         = {1477-9137},
  journal      = {Journal of Cell Science},
  number       = {15},
  publisher    = {The Company of Biologists},
  title        = {{ZnUMBA - a live imaging method to detect local barrier breaches}},
  doi          = {10.1242/jcs.260668},
  volume       = {136},
  year         = {2023},
}

@inproceedings{14083,
  abstract     = {In this work we consider the list-decodability and list-recoverability of arbitrary q-ary codes, for all integer values of q ≥ 2. A code is called (p,L)_q-list-decodable if every radius pn Hamming ball contains less than L codewords; (p,𝓁,L)_q-list-recoverability is a generalization where we place radius pn Hamming balls on every point of a combinatorial rectangle with side length 𝓁 and again stipulate that there be less than L codewords.
Our main contribution is to precisely calculate the maximum value of p for which there exist infinite families of positive rate (p,𝓁,L)_q-list-recoverable codes, the quantity we call the zero-rate threshold. Denoting this value by p_*, we in fact show that codes correcting a p_*+ε fraction of errors must have size O_ε(1), i.e., independent of n. Such a result is typically referred to as a "Plotkin bound." To complement this, a standard random code with expurgation construction shows that there exist positive rate codes correcting a p_*-ε fraction of errors. We also follow a classical proof template (typically attributed to Elias and Bassalygo) to derive from the zero-rate threshold other tradeoffs between rate and decoding radius for list-decoding and list-recovery.
Technically, proving the Plotkin bound boils down to demonstrating the Schur convexity of a certain function defined on the q-simplex as well as the convexity of a univariate function derived from it. We remark that an earlier argument claimed similar results for q-ary list-decoding; however, we point out that this earlier proof is flawed.},
  author       = {Resch, Nicolas and Yuan, Chen and Zhang, Yihan},
  booktitle    = {50th International Colloquium on Automata, Languages, and Programming},
  isbn         = {9783959772785},
  issn         = {1868-8969},
  location     = {Paderborn, Germany},
  publisher    = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik},
  title        = {{Zero-rate thresholds and new capacity bounds for list-decoding and list-recovery}},
  doi          = {10.4230/LIPIcs.ICALP.2023.99},
  volume       = {261},
  year         = {2023},
}

@inproceedings{14084,
  abstract     = {A central problem in computational statistics is to convert a procedure for sampling combinatorial objects into a procedure for counting those objects, and vice versa. We will consider sampling problems which come from Gibbs distributions, which are families of probability distributions over a discrete space Ω with probability mass function of the form μ^Ω_β(ω) ∝ e^{β H(ω)} for β in an interval [β_min, β_max] and H(ω) ∈ {0} ∪ [1, n].
The partition function is the normalization factor Z(β) = ∑_{ω ∈ Ω} e^{β H(ω)}, and the log partition ratio is defined as q = (log Z(β_max))/Z(β_min)
We develop a number of algorithms to estimate the counts c_x using roughly Õ(q/ε²) samples for general Gibbs distributions and Õ(n²/ε²) samples for integer-valued distributions (ignoring some second-order terms and parameters), We show this is optimal up to logarithmic factors. We illustrate with improved algorithms for counting connected subgraphs and perfect matchings in a graph.},
  author       = {Harris, David G. and Kolmogorov, Vladimir},
  booktitle    = {50th International Colloquium on Automata, Languages, and Programming},
  isbn         = {9783959772785},
  issn         = {1868-8969},
  location     = {Paderborn, Germany},
  publisher    = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik},
  title        = {{Parameter estimation for Gibbs distributions}},
  doi          = {10.4230/LIPIcs.ICALP.2023.72},
  volume       = {261},
  year         = {2023},
}

@inproceedings{14085,
  abstract     = {We show an (1+ϵ)-approximation algorithm for maintaining maximum s-t flow under m edge insertions in m1/2+o(1)ϵ−1/2 amortized update time for directed, unweighted graphs. This constitutes the first sublinear dynamic maximum flow algorithm in general sparse graphs with arbitrarily good approximation guarantee.},
  author       = {Goranci, Gramoz and Henzinger, Monika H},
  booktitle    = {50th International Colloquium on Automata, Languages, and Programming},
  isbn         = {9783959772785},
  issn         = {1868-8969},
  location     = {Paderborn, Germany},
  publisher    = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik},
  title        = {{Efficient data structures for incremental exact and approximate maximum flow}},
  doi          = {10.4230/LIPIcs.ICALP.2023.69},
  volume       = {261},
  year         = {2023},
}

@inproceedings{14086,
  abstract     = {The maximization of submodular functions have found widespread application in areas such as machine learning, combinatorial optimization, and economics, where practitioners often wish to enforce various constraints; the matroid constraint has been investigated extensively due to its algorithmic properties and expressive power. Though tight approximation algorithms for general matroid constraints exist in theory, the running times of such algorithms typically scale quadratically, and are not practical for truly large scale settings. Recent progress has focused on fast algorithms for important classes of matroids given in explicit form. Currently, nearly-linear time algorithms only exist for graphic and partition matroids [Alina Ene and Huy L. Nguyen, 2019]. In this work, we develop algorithms for monotone submodular maximization constrained by graphic, transversal matroids, or laminar matroids in time near-linear in the size of their representation. Our algorithms achieve an optimal approximation of 1-1/e-ε and both generalize and accelerate the results of Ene and Nguyen [Alina Ene and Huy L. Nguyen, 2019]. In fact, the running time of our algorithm cannot be improved within the fast continuous greedy framework of Badanidiyuru and Vondrák [Ashwinkumar Badanidiyuru and Jan Vondrák, 2014].
To achieve near-linear running time, we make use of dynamic data structures that maintain bases with approximate maximum cardinality and weight under certain element updates. These data structures need to support a weight decrease operation and a novel Freeze operation that allows the algorithm to freeze elements (i.e. force to be contained) in its basis regardless of future data structure operations. For the laminar matroid, we present a new dynamic data structure using the top tree interface of Alstrup, Holm, de Lichtenberg, and Thorup [Stephen Alstrup et al., 2005] that maintains the maximum weight basis under insertions and deletions of elements in O(log n) time. This data structure needs to support certain subtree query and path update operations that are performed every insertion and deletion that are non-trivial to handle in conjunction. For the transversal matroid the Freeze operation corresponds to requiring the data structure to keep a certain set S of vertices matched, a property that we call S-stability. While there is a large body of work on dynamic matching algorithms, none are S-stable and maintain an approximate maximum weight matching under vertex updates. We give the first such algorithm for bipartite graphs with total running time linear (up to log factors) in the number of edges.},
  author       = {Henzinger, Monika H and Liu, Paul and Vondrák, Jan and Zheng, Da Wei},
  booktitle    = {50th International Colloquium on Automata, Languages, and Programming},
  isbn         = {9783959772785},
  issn         = {18688969},
  location     = {Paderborn, Germany},
  publisher    = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik},
  title        = {{Faster submodular maximization for several classes of matroids}},
  doi          = {10.4230/LIPIcs.ICALP.2023.74},
  volume       = {261},
  year         = {2023},
}

@article{14087,
  abstract     = {Polar active matter of self-propelled particles sustain spontaneous flows through the full-integer topological defects. We study theoretically the incompressible flow profiles around ±1 defects induced by polar and dipolar active forces. We show that dipolar forces induce vortical flows around the +1 defect, while the flow around the −1 defect has an 8-fold rotational symmetry. The vortical flow changes its chirality near the +1 defect core in the absence of the friction with a substrate. We show analytically that the flow induced by polar active forces is vortical near the +1 defect and is 4-fold symmetric near the −1 defect, while it becomes uniform in the far-field. For a pair of oppositely charged defects, this polar flow contributes to a mutual interaction force that depends only on the orientation of the defect pair relative to the background polarization, and that enhances defect pair annihilation. This is in contradiction with the effect of dipolar active forces which decay inversely proportional with the defect separation distance. As such, our analyses reveals a long-ranged mechanism for the pairwise interaction between topological defects in polar active matter.},
  author       = {Rønning, Jonas and Renaud, Julian B and Doostmohammadi, Amin and Angheluta, Luiza},
  issn         = {1744-6848},
  journal      = {Soft Matter},
  pages        = {7513--7527},
  publisher    = {Royal Society of Chemistry},
  title        = {{Spontaneous flows and dynamics of full-integer topological defects in polar active matter}},
  doi          = {10.1039/d3sm00316g},
  volume       = {39},
  year         = {2023},
}

@inproceedings{14105,
  abstract     = {Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter this by aligning the model to the new distribution prior to inference. With no labels available this requires unsupervised objectives to adapt the model on the observed test data. In this paper, we propose Test-Time SelfTraining (TeST): a technique that takes as input a model trained on some source data and a novel data distribution at test time, and learns invariant and robust representations using a student-teacher framework. We find that models adapted using TeST significantly improve over baseline testtime adaptation algorithms. TeST achieves competitive performance to modern domain adaptation algorithms [4, 43], while having access to 5-10x less data at time of adaption. We thoroughly evaluate a variety of baselines on two tasks:
object detection and image segmentation and find that models adapted with TeST. We find that TeST sets the new stateof-the art for test-time domain adaptation algorithms. },
  author       = {Sinha, Samarth and Gehler, Peter and Locatello, Francesco and Schiele, Bernt},
  booktitle    = {2023 IEEE/CVF Winter Conference on Applications of Computer Vision},
  isbn         = {9781665493475},
  issn         = {2642-9381},
  location     = {Waikoloa, HI, United States},
  publisher    = {Institute of Electrical and Electronics Engineers},
  title        = {{TeST: Test-time Self-Training under distribution shift}},
  doi          = {10.1109/wacv56688.2023.00278},
  year         = {2023},
}

@article{14192,
  abstract     = {For the Fröhlich model of the large polaron, we prove that the ground state energy as a function of the total momentum has a unique global minimum at momentum zero. This implies the non-existence of a ground state of the translation invariant Fröhlich Hamiltonian and thus excludes the possibility of a localization transition at finite coupling.},
  author       = {Lampart, Jonas and Mitrouskas, David Johannes and Mysliwy, Krzysztof},
  issn         = {1572-9656},
  journal      = {Mathematical Physics, Analysis and Geometry},
  keywords     = {Geometry and Topology, Mathematical Physics},
  number       = {3},
  publisher    = {Springer Nature},
  title        = {{On the global minimum of the energy–momentum relation for the polaron}},
  doi          = {10.1007/s11040-023-09460-x},
  volume       = {26},
  year         = {2023},
}

@unpublished{14207,
  abstract     = {The binding problem in human cognition, concerning how the brain represents and connects objects within a fixed network of neural connections, remains a subject of intense debate. Most machine learning efforts addressing this issue in an unsupervised setting have focused on slot-based methods, which may be limiting due to their discrete nature and difficulty to express uncertainty. Recently, the Complex AutoEncoder was proposed as an alternative that learns continuous and distributed object-centric representations. However, it is only applicable to simple toy data. In this paper, we present Rotating Features, a generalization of complex-valued features to higher dimensions, and a new evaluation procedure for extracting objects from distributed representations. Additionally, we show the applicability of our approach to pre-trained features. Together, these advancements enable us to scale distributed object-centric representations from simple toy to real-world data. We believe this work advances a new paradigm for addressing the binding problem in machine learning and has the potential to inspire further innovation in the field.},
  author       = {Löwe, Sindy and Lippe, Phillip and Locatello, Francesco and Welling, Max},
  booktitle    = {arXiv},
  title        = {{Rotating features for object discovery}},
  doi          = {10.48550/arXiv.2306.00600},
  year         = {2023},
}

@inproceedings{14208,
  abstract     = {This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification while obtaining (nearly) zero-training error under the lazy training regime. For this purpose, we unify three interrelated concepts of overparameterization, benign overfitting, and the Lipschitz constant of DNNs. Our results indicate that interpolating with smoother functions leads to better generalization. Furthermore, we investigate the special case where interpolating smooth ground-truth functions is performed by DNNs under the Neural Tangent Kernel (NTK) regime for generalization. Our result demonstrates that the generalization error converges to a constant order that only depends on label noise and initialization noise, which theoretically verifies benign overfitting. Our analysis provides a tight lower bound on the normalized margin under non-smooth activation functions, as well as the minimum eigenvalue of NTK under high-dimensional settings, which has its own interest in learning theory.},
  author       = {Zhu, Zhenyu and Liu, Fanghui and Chrysos, Grigorios G and Locatello, Francesco and Cevher, Volkan},
  booktitle    = {Proceedings of the 40th International Conference on Machine Learning},
  location     = {Honolulu, Hawaii, United States},
  pages        = {43105--43128},
  publisher    = {ML Research Press},
  title        = {{Benign overfitting in deep neural networks under lazy training}},
  volume       = {202},
  year         = {2023},
}

@unpublished{14209,
  abstract     = {Diffusion models excel at generating photorealistic images from text-queries. Naturally, many approaches have been proposed to use these generative abilities to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large noisily supervised, but nonetheless, annotated datasets. It is an open question whether the generalization capabilities of diffusion models beyond using the additional data of the pre-training process for augmentation lead to improved downstream performance. We perform a systematic evaluation of existing methods to generate images from diffusion models and study new extensions to assess their benefit for data augmentation. While we find that personalizing diffusion models towards the target data outperforms simpler prompting strategies, we also show that using the training data of the diffusion model alone, via a simple nearest neighbor retrieval procedure, leads to even stronger downstream performance. Overall, our study probes the limitations of diffusion models for data augmentation but also highlights its potential in generating new training data to improve performance on simple downstream vision tasks.},
  author       = {Burg, Max F. and Wenzel, Florian and Zietlow, Dominik and Horn, Max and Makansi, Osama and Locatello, Francesco and Russell, Chris},
  booktitle    = {arXiv},
  title        = {{A data augmentation perspective on diffusion models and retrieval}},
  doi          = {10.48550/arXiv.2304.10253},
  year         = {2023},
}

@unpublished{14210,
  abstract     = {Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on unsupervised and weakly-supervised objectives, prior work missed out on the positive implications for representation learning on real world data. In this work, we propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. Assuming each supervised task only depends on an unknown subset of the factors of variation, we disentangle the feature space of a supervised multi-task model, with features activating sparsely across different tasks and information being shared as appropriate. Importantly, we never directly observe the factors of variations but establish that access to multiple tasks is sufficient for identifiability under sufficiency and minimality assumptions. We validate our approach on six real world distribution shift benchmarks, and different data modalities (images, text), demonstrating how disentangled representations can be transferred to real settings.},
  author       = {Fumero, Marco and Wenzel, Florian and Zancato, Luca and Achille, Alessandro and Rodolà, Emanuele and Soatto, Stefano and Schölkopf, Bernhard and Locatello, Francesco},
  booktitle    = {arXiv},
  title        = {{Leveraging sparse and shared feature activations for disentangled representation learning}},
  doi          = {10.48550/arXiv.2304.07939},
  year         = {2023},
}

@inproceedings{14211,
  abstract     = {Causal discovery methods are intrinsically constrained by the set of assumptions needed to ensure structure identifiability. Moreover additional restrictions are often imposed in order to simplify the inference task: this is the case for the Gaussian noise assumption on additive non-linear models, which is common to many causal discovery approaches. In this paper we show the shortcomings of inference under this hypothesis, analyzing the risk of edge inversion under violation of Gaussianity of the noise terms. Then, we propose a novel method for inferring the topological ordering of the variables in the causal graph, from data generated according to an additive non-linear model with a generic noise distribution. This leads to NoGAM (Not only Gaussian Additive noise Models), a causal discovery algorithm with a minimal set of assumptions and state of the art performance, experimentally benchmarked on synthetic data.},
  author       = {Montagna, Francesco and Noceti, Nicoletta and Rosasco, Lorenzo and Zhang, Kun and Locatello, Francesco},
  booktitle    = {2nd Conference on Causal Learning and Reasoning},
  location     = {Tübingen, Germany},
  title        = {{Causal discovery with score matching on additive models with arbitrary noise}},
  year         = {2023},
}