DOI,IST REx ID,Research Group,Title of publication
null,12859,"GradSch,MaMo",Beyond the universal law of robustness: Sharper laws for random features and neural tangent kernels
10.1073/pnas.2302028120,13315,MaMo,Fundamental limits in structured principal component analysis and how to reach them
10.1109/ITW55543.2023.10160238,13321,MaMo,Approximate message passing for multi-layer estimation in rotationally invariant models
null,14921,"MaMo,ChLa",Deep neural collapse is provably optimal for the deep unconstrained features model
10.1109/isit54713.2023.10206899,14922,MaMo,Concentration without independence via information measures
10.1109/isit54713.2023.10206671,14923,MaMo,Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise
null,14924,MaMo,"Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence"
null,14459,"MaMo,DaAl","Fundamental limits of two-layer autoencoders, and achieving them with gradient methods"
10.1109/tcomm.2022.3211101,12233,MaMo,Decoding Reed-Muller codes with successive codeword permutations
10.1088/1742-5468/ac9828,12480,MaMo,Approximate message passing with spectral initialization for generalized linear models
10.48550/arXiv.2205.10009,12536,MaMo,The price of ignorance: How much does it cost to forget noise structure in low-rank matrix estimation?
null,12537,MaMo,Memorization and optimization in deep neural networks with minimum over-parameterization
10.1109/ITW54588.2022.9965870,12538,MaMo,Sharp asymptotics on the compression of two-layer neural networks
null,12540,MaMo,Estimation in rotationally invariant generalized linear models via approximate message passing
10.1109/TWC.2021.3125626,10364,MaMo,Parallelism versus latency in simplified successive-cancellation decoding of polar codes
null,11420,"MaMo,DaAl",Mean-field analysis of piecewise linear solutions for wide ReLU networks
10.1109/ISIT50566.2022.9834712,12016,MaMo,Polar coded computing: The role of the scaling exponent
null,13146,MaMo,Tight bounds on the smallest Eigenvalue of the neural tangent kernel for deep ReLU networks
10.1109/TIT.2020.3038806,9002,MaMo,Binary linear codes with optimal scaling: Polar codes with large kernels
10.1109/TWC.2020.3022922,9047,MaMo,Sublinear latency for simplified successive cancellation decoding of polar codes