Mikhail Belkin

49 papers · 2006–2025 · 10 venues · across top CS/AI venues

This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 17 separate collaboration groups - the largest holds only 35% of them. Pick the group below that matches the researcher you mean. How a shared name is split.

Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.

Which Mikhail Belkin?

5 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.

with Luis Rademacher, Chaoyue Liu, Libin Zhu 17 papers · 2013–2025 · ICML, NeurIPS, COLT Hide ▲

Emergence in non-neural models: grokking modular arithmetic via average gradient outer product ICML 2025 Task Generalization with Autoregressive Compositional Structure: Can Learning from D Tasks Generalize to D^T Tasks? ICML 2025 UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models NAACL 2025 Average gradient outer product as a mechanism for deep neural collapse NeurIPS 2024 Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning ICML 2024 On the Nyström Approximation for Preconditioning in Kernel Machines AISTATS 2024 Quadratic models for understanding catapult dynamics of neural networks ICLR 2024 Uncertainty Estimation with Recursive Feature Machines UAI 2024 Neural tangent kernel at initialization: linear width suffices UAI 2023 Toward Large Kernel Models ICML 2023 Accelerating SGD with momentum for over-parameterized learning ICLR 2020 Basis Learning as an Algorithmic Primitive COLT 2016 Clustering with Bregman Divergences: an Asymptotic Analysis NeurIPS 2016 A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA NeurIPS 2015 The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures COLT 2014 Blind Signal Separation in the Presence of Gaussian Noise COLT 2013 Fast Algorithms for Gaussian Noise Invariant Independent Component Analysis NeurIPS 2013

with Yusu Wang, Qichao Que, Justin Eldridge 9 papers · 2011–2018 · NeurIPS, AISTATS, COLT Show ▼

with SIYUAN MA, Like Hui, Soumik Mandal 6 papers · 2017–2023 · ICML, ICLR, Interspeech Show ▼

with Partha Niyogi, Hariharan Narayanan, Vikas Sindhwani 3 papers · 2006 · NeurIPS, JMLR Show ▼

with Kaushik Sinha 2 papers · 2007–2009 · NeurIPS Show ▼

12 papers whose co-authors appear nowhere else under this name

A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis COLT 2025 More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory ICLR 2024 Classification vs regression in overparameterized regimes: Does the loss function matter? JMLR 2021 Conference on Learning Theory 2021: Post-conference Preface COLT 2021 Multiple Descent: Design Your Own Generalization Curve NeurIPS 2021 Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures NeurIPS 2021 Does data interpolation contradict statistical optimality? AISTATS 2019 Approximation beats concentration? An approximation view on inference with smooth radial kernels COLT 2018 Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate NeurIPS 2018 Learning privately from multiparty data ICML 2016 Laplacian Support Vector Machines Trained in the Primal JMLR 2011 On Learning with Integral Operators JMLR 2010

Venues · all papers under this name

NeurIPS (16) COLT (8) ICML (8) AISTATS (4) ICLR (4) JMLR (4) UAI (2) ALT (1) Interspeech (1) NAACL (1)