Skip to content

Mikhail Belkin

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

44

Venues

15

Active years

2004–2025

Best venue rank

A*

Where they publish

Papers

44 indexed papers, newest first.

YearVenueTitleAuthors
2025COLTA Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis.Akash Kumar, Rahul Parhi, Mikhail Belkin
2025ICMLTask Generalization with Autoregressive Compositional Structure: Can Learning from D Tasks Generalize to DT Tasks?Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen, Hongzhou Lin, Jingzhao Zhang, Mikhail Belkin
2025ICMLEmergence in non-neural models: grokking modular arithmetic via average gradient outer product.Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin
2025NAACLUNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models.Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, Ramn Huerta, Ivan Vulic
2024AISTATSOn the Nystrm Approximation for Preconditioning in Kernel Machines.Amirhesam Abedsoltan, Parthe Pandit, Luis Rademacher, Mikhail Belkin
2024ICLRMore is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory.James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin
2024ICLRQuadratic models for understanding catapult dynamics of neural networks.Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2024ICMLCatapults in SGD: spikes in the training loss and their impact on generalization through feature learning.Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2024UAIUncertainty Estimation with Recursive Feature Machines.Daniel Gedon, Amirhesam Abedsoltan, Thomas B. Schn, Mikhail Belkin
2023ICLRRestricted Strong Convexity of Deep Learning Models with Smooth Activations.Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2023ICMLToward Large Kernel Models.Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit
2023ICMLCut your Losses with Squentropy.Like Hui, Mikhail Belkin, Stephen Wright
2023UAINeural tangent kernel at initialization: linear width suffices.Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2022ICLRTransition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models.Chaoyue Liu, Libin Zhu, Mikhail Belkin
2021ICLREvaluation of Neural Architectures trained with square Loss vs Cross-Entropy in Classification Tasks.Like Hui, Mikhail Belkin
2020ICLRAccelerating SGD with momentum for over-parameterized learning.Chaoyue Liu, Mikhail Belkin
2019AISTATSDoes data interpolation contradict statistical optimality?Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov
2019InterspeechKernel Machines Beat Deep Neural Networks on Mask-Based Single-Channel Speech Enhancement.Like Hui, Siyuan Ma, Mikhail Belkin
2018ALTUnperturbed: spectral analysis beyond Davis-Kahan.Justin Eldridge, Mikhail Belkin, Yusu Wang
2018COLTApproximation beats concentration? An approximation view on inference with smooth radial kernels.Mikhail Belkin
2018ICMLTo Understand Deep Learning We Need to Understand Kernel Learning.Mikhail Belkin, Siyuan Ma, Soumik Mandal
2018ICMLThe Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning.Siyuan Ma, Raef Bassily, Mikhail Belkin
2016AAAIThe Hidden Convexity of Spectral Clustering.James R. Voss, Mikhail Belkin, Luis Rademacher
2016AISTATSBack to the Future: Radial Basis Function Networks Revisited.Qichao Que, Mikhail Belkin
2016COLTBasis Learning as an Algorithmic Primitive.Mikhail Belkin, Luis Rademacher, James R. Voss
2016ICMLLearning privately from multiparty data.Jihun Hamm, Yingjun Cao, Mikhail Belkin
2015COLTBeyond Hartigan Consistency: Merge Distortion Metric for Hierarchical Clustering.Justin Eldridge, Mikhail Belkin, Yusu Wang
2015ICDCSCrowd-ML: A Privacy-Preserving Learning Framework for a Crowd of Smart Devices.Jihun Hamm, Adam C. Champion, Guoxing Chen, Mikhail Belkin, Dong Xuan
2014COLTThe More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures.Joseph Anderson, Mikhail Belkin, Navin Goyal, Luis Rademacher, James R. Voss
2013COLTBlind Signal Separation in the Presence of Gaussian Noise.Mikhail Belkin, Luis Rademacher, James R. Voss
2011KDDAn iterated graph laplacian approach for ranking on manifolds.Xueyuan Zhou, Mikhail Belkin, Nathan Srebro
2010COLTToward Learning Gaussian Mixtures with Arbitrary Separation.Mikhail Belkin, Kaushik Sinha
2010FOCSPolynomial Learning of Distribution Families.Mikhail Belkin, Kaushik Sinha
2010InterspeechLearning speaker normalization using semisupervised manifold alignment.Andrew R. Plummer, Mary E. Beckman, Mikhail Belkin, Eric Fosler-Lussier, Benjamin Munson
2009COLTA Note on Learning with Integral Operators.Lorenzo Rosasco, Mikhail Belkin, Ernesto De Vito
2009SODAConstructing Laplace operator from point clouds inMikhail Belkin, Jian Sun, Yusu Wang
2008ICMLData spectroscopy: learning mixture models using eigenspaces of convolution operators.Tao Shi, Mikhail Belkin, Bin Yu
2008ICPRProbabilistic mixtures of differential profiles for shape recognition.Lei Ding, Mikhail Belkin
2006FOCSHeat Flow and a Faster Algorithm to Compute the Surface Area of a Convex Body.Mikhail Belkin, Hariharan Narayanan, Partha Niyogi
2005COLTTowards a Theoretical Foundation for Laplacian-Based Manifold Methods.Mikhail Belkin, Partha Niyogi
2005ICMLBeyond the point cloud: from transductive to semi-supervised learning.Vikas Sindhwani, Partha Niyogi, Mikhail Belkin
2004COLTRegularization and Semi-supervised Learning on Large Graphs.Mikhail Belkin, Irina Matveeva, Partha Niyogi
2004COLTOn the Convergence of Spectral Clustering on Random Samples: The Normalized Case.Ulrike von Luxburg, Olivier Bousquet, Mikhail Belkin
2004ICASSPTikhonov regularization and semi-supervised learning on large graphs.Mikhail Belkin, Irina Matveeva, Partha Niyogi