Mikhail Belkin

According to our database, Mikhail Belkin authored at least 117 papers between 2001 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Emergence in non-neural models: grokking modular arithmetic via average gradient outer product.

Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin

CoRR, 2024

Average gradient outer product as a mechanism for deep neural collapse.

Daniel Beaglehole, Peter Súkeník, Marco Mondelli, Mikhail Belkin

CoRR, 2024

Unmemorization in Large Language Models via Self-Distillation and Deliberate Imagination.

Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, Ramón Huerta, Ivan Vulic

CoRR, 2024

Linear Recursive Feature Machines provably recover low-rank matrices.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Dmitriy Drusvyatskiy

CoRR, 2024

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning.

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Quadratic models for understanding catapult dynamics of neural networks.

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

Proceedings of the Twelfth International Conference on Learning Representations, 2024

More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory.

James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin

Proceedings of the Twelfth International Conference on Learning Representations, 2024

On the Nyström Approximation for Preconditioning in Kernel Machines.

Amirhesam Abedsoltan, Parthe Pandit, Luis Rademacher, Mikhail Belkin

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors.

Nikhil Ghosh, Mikhail Belkin

SIAM J. Math. Data Sci., December, 2023

On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions.

Daniel Beaglehole, Mikhail Belkin, Parthe Pandit

SIAM J. Math. Data Sci., December, 2023

More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory.

James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin

CoRR, 2023

Mechanism of feature learning in convolutional neural networks.

Daniel Beaglehole, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin

CoRR, 2023

Aiming towards the minimizers: fast convergence of SGD for overparametrized problems.

Chaoyue Liu, Dmitriy Drusvyatskiy, Mikhail Belkin, Damek Davis, Yi-An Ma

CoRR, 2023

On Emergence of Clean-Priority Learning in Early Stopped Neural Networks.

Chaoyue Liu, Amirhesam Abedsoltan, Mikhail Belkin

CoRR, 2023

Neural tangent kernel at initialization: linear width suffices.

Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Cut your Losses with Squentropy.

Like Hui, Mikhail Belkin, Stephen Wright

Proceedings of the International Conference on Machine Learning, 2023

Toward Large Kernel Models.

Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit

Proceedings of the International Conference on Machine Learning, 2023

2022

Feature learning in neural networks and kernel machines that recursively learn features.

Adityanarayanan Radhakrishnan, Daniel Beaglehole, Parthe Pandit, Mikhail Belkin

CoRR, 2022

Restricted Strong Convexity of Deep Learning Models with Smooth Activations.

Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin

CoRR, 2022

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting.

Neil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit, Mikhail Belkin, Preetum Nakkiran

CoRR, 2022

A note on Linear Bottleneck networks and their Transition to Multilinearity.

Libin Zhu, Parthe Pandit, Mikhail Belkin

CoRR, 2022

Kernel Ridgeless Regression is Inconsistent for Low Dimensions.

Daniel Beaglehole, Mikhail Belkin, Parthe Pandit

CoRR, 2022

Quadratic models for understanding neural network dynamics.

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

CoRR, 2022

Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture.

Libin Zhu, Chaoyue Liu, Mikhail Belkin

CoRR, 2022

Wide and Deep Neural Networks Achieve Optimality for Classification.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2022

Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models.

Chaoyue Liu, Libin Zhu, Mikhail Belkin

CoRR, 2022

Limitations of Neural Collapse for Understanding Generalization in Deep Learning.

Like Hui, Mikhail Belkin, Preetum Nakkiran

CoRR, 2022

Benign Overfitting in Two-layer Convolutional Neural Networks.

Yuan Cao, Zixiang Chen, Mikhail Belkin, Quanquan Gu

CoRR, 2022

2021

Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation.

Mikhail Belkin

Acta Numer., May, 2021

Classification vs regression in overparameterized regimes: Does the loss function matter?

Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin, Daniel Hsu, Anant Sahai

J. Mach. Learn. Res., 2021

Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2021

Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks.

Adityanarayanan Radhakrishnan, George Stefanakis, Mikhail Belkin, Caroline Uhler

CoRR, 2021

Multiple Descent: Design Your Own Generalization Curve.

Lin Chen, Yifei Min, Mikhail Belkin, Amin Karbasi

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures.

Yuan Cao, Quanquan Gu, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Evaluation of Neural Architectures trained with square Loss vs Cross-Entropy in Classification Tasks.

Like Hui, Mikhail Belkin

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Two Models of Double Descent for Weak Features.

Mikhail Belkin, Daniel Hsu, Ji Xu

SIAM J. Math. Data Sci., 2020

Overparameterized neural networks implement associative memory.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

Proc. Natl. Acad. Sci. USA, 2020

Back to the Future: Radial Basis Function Network Revisited.

Qichao Que, Mikhail Belkin

IEEE Trans. Pattern Anal. Mach. Intell., 2020

Linear Convergence and Implicit Regularization of Generalized Mirror Descent with Time-Dependent Mirrors.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2020

Toward a theory of optimization for over-parameterized systems of non-linear equations: the lessons of deep learning.

Chaoyue Liu, Libin Zhu, Mikhail Belkin

CoRR, 2020

On the linearity of large non-linear models: when and why the tangent kernel is constant.

Chaoyue Liu, Libin Zhu, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Accelerating SGD with momentum for over-parameterized learning.

Chaoyue Liu, Mikhail Belkin

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Overparameterized Neural Networks Can Implement Associative Memory.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2019

Kernel Machines That Adapt To Gpus For Effective Large Batch Training.

Siyuan Ma, Mikhail Belkin

Proceedings of the Second Conference on Machine Learning and Systems, SysML 2019, 2019

Kernel Machines Beat Deep Neural Networks on Mask-Based Single-Channel Speech Enhancement.

Like Hui, Siyuan Ma, Mikhail Belkin

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Does data interpolation contradict statistical optimality?

Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Eigenvectors of Orthogonally Decomposable Functions.

Mikhail Belkin, Luis Rademacher, James R. Voss

SIAM J. Comput., 2018

Reconciling modern machine learning and the bias-variance trade-off.

Mikhail Belkin, Daniel Hsu, Siyuan Ma, Soumik Mandal

CoRR, 2018

On exponential convergence of SGD in non-convex over-parametrized learning.

Raef Bassily, Mikhail Belkin, Siyuan Ma

CoRR, 2018

MaSS: an Accelerated Stochastic Method for Over-parametrized Learning.

Chaoyue Liu, Mikhail Belkin

CoRR, 2018

Downsampling leads to Image Memorization in Convolutional Autoencoders.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2018

Learning kernels that adapt to GPU.

Siyuan Ma, Mikhail Belkin

CoRR, 2018

Parametrized Accelerated Methods Free of Condition Number.

Chaoyue Liu, Mikhail Belkin

CoRR, 2018

Fast Interactive Image Retrieval using large-scale unlabeled data.

Akshay Mehra, Jihun Hamm, Mikhail Belkin

CoRR, 2018

Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate.

Mikhail Belkin, Daniel J. Hsu, Partha Mitra

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning.

Siyuan Ma, Raef Bassily, Mikhail Belkin

Proceedings of the 35th International Conference on Machine Learning, 2018

To Understand Deep Learning We Need to Understand Kernel Learning.

Mikhail Belkin, Siyuan Ma, Soumik Mandal

Proceedings of the 35th International Conference on Machine Learning, 2018

Approximation beats concentration? An approximation view on inference with smooth radial kernels.

Mikhail Belkin

Proceedings of the Conference On Learning Theory, 2018

Unperturbed: spectral analysis beyond Davis-Kahan.

Justin Eldridge, Mikhail Belkin, Yusu Wang

Proceedings of the Algorithmic Learning Theory, 2018

2017

Diving into the shallows: a computational perspective on large-scale shallow learning.

Siyuan Ma, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

2016

Learning Privately from Multiparty Data.

Jihun Hamm, Paul Cao, Mikhail Belkin

CoRR, 2016

Clustering with Bregman Divergences: an Asymptotic Analysis.

Chaoyue Liu, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Graphons, mergeons, and so on!

Justin Eldridge, Mikhail Belkin, Yusu Wang

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Learning privately from multiparty data.

Jihun Hamm, Yingjun Cao, Mikhail Belkin

Proceedings of the 33nd International Conference on Machine Learning, 2016

Basis Learning as an Algorithmic Primitive.

Mikhail Belkin, Luis Rademacher, James R. Voss

Proceedings of the 29th Conference on Learning Theory, 2016

Back to the Future: Radial Basis Function Networks Revisited.

Qichao Que, Mikhail Belkin

Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

The Hidden Convexity of Spectral Clustering.

James R. Voss, Mikhail Belkin, Luis Rademacher

Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016

2015

Polynomial Learning of Distribution Families.

Mikhail Belkin, Kaushik Sinha

SIAM J. Comput., 2015

Optimal Recovery in Noisy ICA.

James R. Voss, Mikhail Belkin, Luis Rademacher

CoRR, 2015

Probabilistic Zero-shot Classification with Semantic Rankings.

Jihun Hamm, Mikhail Belkin

CoRR, 2015

A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA.

James R. Voss, Mikhail Belkin, Luis Rademacher

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Crowd-ML: A Privacy-Preserving Learning Framework for a Crowd of Smart Devices.

Jihun Hamm, Adam C. Champion, Guoxing Chen, Mikhail Belkin, Dong Xuan

Proceedings of the 35th IEEE International Conference on Distributed Computing Systems, 2015

Microwave-Band Circuit-Level Semiconductor Laser Modeling.

Mikhail Belkin, Vladimir Iakovlev

Proceedings of the 2015 IEEE European Modelling Symposium, 2015

Beyond Hartigan Consistency: Merge Distortion Metric for Hierarchical Clustering.

Justin Eldridge, Mikhail Belkin, Yusu Wang

Proceedings of The 28th Conference on Learning Theory, 2015

2014

Learning a Hidden Basis Through Imperfect Measurements: An Algorithmic Primitive.

Mikhail Belkin, Luis Rademacher, James R. Voss

CoRR, 2014

Learning with Fredholm Kernels.

Qichao Que, Mikhail Belkin, Yusu Wang

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures.

Joseph Anderson, Mikhail Belkin, Navin Goyal, Luis Rademacher, James R. Voss

Proceedings of The 27th Conference on Learning Theory, 2014

2013

Heat flow and a faster algorithm to compute the surface area of a convex body.

Mikhail Belkin, Hariharan Narayanan, Partha Niyogi

Random Struct. Algorithms, 2013

Fast Algorithms for Gaussian Noise Invariant Independent Component Analysis.

James R. Voss, Luis Rademacher, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Inverse Density as an Inverse Problem: the Fredholm Equation Approach.

Qichao Que, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Blind Signal Separation in the Presence of Gaussian Noise.

Mikhail Belkin, Luis Rademacher, James R. Voss

Proceedings of the COLT 2013, 2013

2012

Toward Understanding Complex Spaces: Graph Laplacians on Manifolds with Singularities and Boundaries.

Mikhail Belkin, Qichao Que, Yusu Wang, Xueyuan Zhou

Proceedings of the COLT 2012, 2012

Graph Laplacians on Singular Manifolds: Toward understanding complex spaces: graph Laplacians on manifolds with singularities and boundaries

Mikhail Belkin, Qichao Que, Yusu Wang, Xueyuan Zhou

CoRR, 2012

Metric Based Automatic Event Segmentation.

Yuwen Zhuang, Mikhail Belkin, Simon Dennis

Proceedings of the Mobile Computing, Applications, and Services, 2012

Automatic Annotation of Daily Activity from Smartphone-Based Multisensory Streams.

Jihun Hamm, Benjamin Stone, Mikhail Belkin, Simon Dennis

Proceedings of the Mobile Computing, Applications, and Services, 2012

2011

Semi-supervised Learning by Higher Order Regularization.

Xueyuan Zhou, Mikhail Belkin

Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

Laplacian Support Vector Machines Trained in the Primal.

Stefano Melacci, Mikhail Belkin

J. Mach. Learn. Res., 2011

Behavior of Graph Laplacians on Manifolds with Boundary

Xueyuan Zhou, Mikhail Belkin

CoRR, 2011

Data Skeletonization via Reeb Graphs.

Xiaoyin Ge, Issam Safa, Mikhail Belkin, Yusu Wang

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

An iterated graph laplacian approach for ranking on manifolds.

Xueyuan Zhou, Mikhail Belkin, Nathan Srebro

Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2011

2010

On Learning with Integral Operators.

Lorenzo Rosasco, Mikhail Belkin, Ernesto De Vito

J. Mach. Learn. Res., 2010

Learning speaker normalization using semisupervised manifold alignment.

Andrew R. Plummer, Mary E. Beckman, Mikhail Belkin, Eric Fosler-Lussier, Benjamin Munson

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Toward Learning Gaussian Mixtures with Arbitrary Separation.

Mikhail Belkin, Kaushik Sinha

Proceedings of the COLT 2010, 2010

2009

Learning Gaussian Mixtures with Arbitrary Separation

Mikhail Belkin, Kaushik Sinha

CoRR, 2009

Constructing Laplace operator from point clouds in <i>R</i>^<i>d</i>.

Mikhail Belkin, Jian Sun, Yusu Wang

Proceedings of the Twentieth Annual ACM-SIAM Symposium on Discrete Algorithms, 2009

Semi-supervised Learning using Sparse Eigenfunction Bases.

Kaushik Sinha, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

A Note on Learning with Integral Operators.

Lorenzo Rosasco, Mikhail Belkin, Ernesto De Vito

Proceedings of the COLT 2009, 2009

2008

Towards a theoretical foundation for Laplacian-based manifold methods.

Mikhail Belkin, Partha Niyogi

J. Comput. Syst. Sci., 2008

Component based shape retrieval using differential profiles.

Lei Ding, Mikhail Belkin

Proceedings of the 1st ACM SIGMM International Conference on Multimedia Information Retrieval, 2008

Probabilistic mixtures of differential profiles for shape recognition.

Lei Ding, Mikhail Belkin

Proceedings of the 19th International Conference on Pattern Recognition (ICPR 2008), 2008

Data spectroscopy: learning mixture models using eigenspaces of convolution operators.

Tao Shi, Mikhail Belkin, Bin Yu

Proceedings of the Machine Learning, 2008

Discrete laplace operator on meshed surfaces.

Mikhail Belkin, Jian Sun, Yusu Wang

Proceedings of the 24th ACM Symposium on Computational Geometry, 2008

2007

The Value of Labeled and Unlabeled Examples when the Model is Imperfect.

Kaushik Sinha, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 20, 2007

2006

Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples.

Mikhail Belkin, Partha Niyogi, Vikas Sindhwani

J. Mach. Learn. Res., 2006

On the Relation Between Low Density Separation, Spectral Clustering and Graph Cuts.

Hariharan Narayanan, Mikhail Belkin, Partha Niyogi

Proceedings of the Advances in Neural Information Processing Systems 19, 2006

Convergence of Laplacian Eigenmaps.

Mikhail Belkin, Partha Niyogi

Proceedings of the Advances in Neural Information Processing Systems 19, 2006

2005

Margin Semi-Supervised Learning for Structured Variables.

Yasemin Altun, David A. McAllester, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005

Beyond the point cloud: from transductive to semi-supervised learning.

Vikas Sindhwani, Partha Niyogi, Mikhail Belkin

Proceedings of the Machine Learning, 2005

2004

Semi-Supervised Learning on Riemannian Manifolds.

Mikhail Belkin, Partha Niyogi

Mach. Learn., 2004

Limits of Spectral Clustering.

Ulrike von Luxburg, Olivier Bousquet, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Tikhonov regularization and semi-supervised learning on large graphs.

Mikhail Belkin, Irina Matveeva, Partha Niyogi

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

On the Convergence of Spectral Clustering on Random Samples: The Normalized Case.

Ulrike von Luxburg, Olivier Bousquet, Mikhail Belkin

Proceedings of the Learning Theory, 17th Annual Conference on Learning Theory, 2004

Regularization and Semi-supervised Learning on Large Graphs.

Mikhail Belkin, Irina Matveeva, Partha Niyogi

Proceedings of the Learning Theory, 17th Annual Conference on Learning Theory, 2004

2003

Laplacian Eigenmaps for Dimensionality Reduction and Data Representation.

Mikhail Belkin, Partha Niyogi

Neural Comput., 2003

2002

Using eigenvectors of the bigram graph to infer morpheme identity.

Mikhail Belkin, John A. Goldsmith

Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, 2002

Using Manifold Stucture for Partially Labeled Classification.

Mikhail Belkin, Partha Niyogi

Proceedings of the Advances in Neural Information Processing Systems 15 [Neural Information Processing Systems, 2002

2001

Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering.

Mikhail Belkin, Partha Niyogi

Proceedings of the Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, 2001