DOI,IST REx ID,Research Group,Title of publication
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,14921,"MaMo,ChLa",Deep neural collapse is provably optimal for the deep unconstrained features model
10.1109/ITW55543.2023.10160238,13321,MaMo,Approximate message passing for multi-layer estimation in rotationally invariant models
10.1109/tit.2023.3257239,14751,MaMo,Zero-error communication over adversarial MACs
10.1109/TIT.2023.3292219,13269,MaMo,Codes for the Z-channel
null,12859,"GradSch,MaMo",Beyond the universal law of robustness: Sharper laws for random features and neural tangent kernels
10.1109/isit54713.2023.10206899,14922,MaMo,Concentration without independence via information measures
10.4230/LIPIcs.ICALP.2023.99,14083,MaMo,Zero-rate thresholds and new capacity bounds for list-decoding and list-recovery
null,14459,"MaMo,DaAl","Fundamental limits of two-layer autoencoders, and achieving them with gradient methods"
10.1109/TIT.2022.3189542,11639,MaMo,List decoding random Euclidean codes and Infinite constellations
10.1109/ISIT50566.2022.9834709,12011,MaMo,The capacity of causal adversarial channels
10.1109/ISIT50566.2022.9834711,12012,MaMo,Heterogeneous differential privacy via graphs
10.1109/ISIT50566.2022.9834850,12013,MaMo,On the capacity of additive AVCs with feedback
10.1109/ISIT50566.2022.9834512,12014,MaMo,List-decodability of Poisson Point Processes
10.1109/ISIT50566.2022.9834443,12015,MaMo,Lower bounds for multiple packing
10.1109/ISIT50566.2022.9834712,12016,MaMo,Polar coded computing: The role of the scaling exponent
10.1088/1742-5468/ac9828,12480,MaMo,Approximate message passing with spectral initialization for generalized linear models
10.1109/ITW54588.2022.9965870,12538,MaMo,Sharp asymptotics on the compression of two-layer neural networks
10.48550/arXiv.2203.16701,12860,"GradSch,MaMo",Towards differential relational privacy and its use in question answering