_id,title
14459,"Fundamental limits of two-layer autoencoders, and achieving them with gradient methods"
14665,Multiple packing: Lower bounds via error exponents
14751,Zero-error communication over adversarial MACs
14921,Deep neural collapse is provably optimal for the deep unconstrained features model
14922,Concentration without independence via information measures
14923,Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise
14924,"Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence"
13269,Codes for the Z-channel
13315,Fundamental limits in structured principal component analysis and how to reach them
13321,Approximate message passing for multi-layer estimation in rotationally invariant models
14083,Zero-rate thresholds and new capacity bounds for list-decoding and list-recovery
12838,Multiple packing: Lower bounds via infinite constellations
12859,Beyond the universal law of robustness: Sharper laws for random features and neural tangent kernels
11420,Mean-field analysis of piecewise linear solutions for wide ReLU networks
11639,List decoding random Euclidean codes and Infinite constellations
10364,Parallelism versus latency in simplified successive-cancellation decoding of polar codes
12011,The capacity of causal adversarial channels
12012,Heterogeneous differential privacy via graphs
12013,On the capacity of additive AVCs with feedback
12014,List-decodability of Poisson Point Processes