Mikhail Belkin

发表

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

Raef Bassily, Mikhail Belkin, Siyuan Ma, 2018, ArXiv.

Behavior of Graph Laplacians on Manifolds with Boundary pdf

Mikhail Belkin, Xueyuan Zhou, Mikhail Belkin, 2011, ArXiv.

New directions in gaussian mixture learning and semi-supervised learning

Mikhail Belkin, Kaushik Sinha, Mikhail Belkin, 2010 .

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

Mikhail Belkin, Mikhail Belkin, M. Belkin, 2018, COLT.

Using Manifold Stucture for Partially Labeled Classification

Mikhail Belkin, Partha Niyogi, Mikhail Belkin, 2002, NIPS.

To understand deep learning we need to understand kernel learning pdf

Mikhail Belkin, Siyuan Ma, Soumik Mandal, 2018, ICML.

Accelerating SGD with momentum for over-parameterized learning

Mikhail Belkin, Chaoyue Liu, Mikhail Belkin, 2018, ICLR.

Graphons, mergeons, and so on!

Mikhail Belkin, Yusu Wang, Justin Eldridge, 2016, NIPS.

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

Mikhail Belkin, Daniel J. Hsu, Partha Mitra, 2018, NeurIPS.

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

Mikhail Belkin, Yusu Wang, Xueyuan Zhou, 2012, COLT.

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

Mikhail Belkin, Chaoyue Liu, Mikhail Belkin, 2018, ArXiv.

Polynomial Learning of Distribution Families

Mikhail Belkin, Kaushik Sinha, 2010, FOCS.

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

Mikhail Belkin, Libin Zhu, Chaoyue Liu, 2020, ArXiv.

Optimal Recovery in Noisy ICA pdf

Mikhail Belkin, Luis Rademacher, James R. Voss, 2015, ArXiv.

Learning kernels that adapt to GPU pdf

Mikhail Belkin, Siyuan Ma, Mikhail Belkin, 2018, ArXiv.

The dimensionality of episodic images

Mikhail Belkin, Vishnu Sreekumar, Yuwen Zhuang, 2010 .

Does data interpolation contradict statistical optimality? pdf

Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov, 2018, AISTATS.

Overparameterized neural networks implement associative memory

Mikhail Belkin, Caroline Uhler, Adityanarayanan Radhakrishnan, 2019, Proceedings of the National Academy of Sciences.

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

Mikhail Belkin, Vikas Sindhwani, Partha Niyogi, 2006, J. Mach. Learn. Res..

On Learning with Integral Operators

Mikhail Belkin, Lorenzo Rosasco, Ernesto De Vito, 2010, J. Mach. Learn. Res..

Semi-Supervised Learning on Riemannian Manifolds

Mikhail Belkin, Partha Niyogi, Mikhail Belkin, 2004, Machine Learning.

Unperturbed: spectral analysis beyond Davis-Kahan pdf

Mikhail Belkin, Yusu Wang, Justin Eldridge, 2017, ALT.

Toward Learning Gaussian Mixtures with Arbitrary Separation

Mikhail Belkin, Kaushik Sinha, 2010, COLT.

Inverse Density as an Inverse Problem: the Fredholm Equation Approach

Mikhail Belkin, Qichao Que, Mikhail Belkin, 2013, NIPS.

Basis Learning as an Algorithmic Primitive

Mikhail Belkin, Luis Rademacher, James R. Voss, 2014, COLT.

The Hidden Convexity of Spectral Clustering pdf

Mikhail Belkin, Luis Rademacher, James R. Voss, 2014, AAAI.

Tikhonov regularization and semi-supervised learning on large graphs

Mikhail Belkin, Partha Niyogi, Irina Matveeva, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Margin Semi-Supervised Learning for Structured Variables

Mikhail Belkin, Yasemin Altun, David A. McAllester, 2005, NIPS.

Semi-supervised Learning by Higher Order Regularization

Mikhail Belkin, Xueyuan Zhou, Mikhail Belkin, 2011, AISTATS.

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

Mikhail Belkin, Luis Rademacher, James R. Voss, 2014, ArXiv.

Convergence of Laplacian Eigenmaps

Mikhail Belkin, Partha Niyogi, Mikhail Belkin, 2006, NIPS.

Automatic Annotation of Daily Activity from Smartphone-Based Multisensory Streams

Mikhail Belkin, Simon Dennis, Jihun Hamm, 2012, MobiCASE.

Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering

Mikhail Belkin, Partha Niyogi, Mikhail Belkin, 2001, NIPS.

Reconciling modern machine-learning practice and the classical bias–variance trade-off

Mikhail Belkin, Daniel J. Hsu, Daniel Hsu, 2018, Proceedings of the National Academy of Sciences.

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

Mikhail Belkin, Caroline Uhler, Adityanarayanan Radhakrishnan, 2020, ArXiv.

Back to the Future: Radial Basis Function Network Revisited

Mikhail Belkin, Qichao Que, Mikhail Belkin, 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Microwave-Band Circuit-Level Semiconductor Laser Modeling

Mikhail Belkin, Vladimir Iakovlev, 2015, 2015 IEEE European Modelling Symposium (EMS).

A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA

Mikhail Belkin, Luis Rademacher, James R. Voss, 2015, NIPS.

An iterated graph laplacian approach for ranking on manifolds

Mikhail Belkin, Nathan Srebro, Xueyuan Zhou, 2011, KDD.

Clustering with Bregman Divergences: an Asymptotic Analysis

Mikhail Belkin, Chaoyue Liu, Mikhail Belkin, 2016, NIPS.

Learning privately from multiparty data

Mikhail Belkin, Yingjun Cao, Jihun Hamm, 2016, ICML.

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

Mikhail Belkin, Joseph Anderson, Navin Goyal, 2013, COLT.

Data spectroscopy: learning mixture models using eigenspaces of convolution operators

Mikhail Belkin, Bin Yu, Tao Shi, 2008, ICML '08.

Semi-Supervised Learning Using Sparse Eigenfunction Bases

Mikhail Belkin, Kaushik Sinha, Mikhail Belkin, 2009, AAAI Fall Symposium: Manifold Learning and Its Applications.

Memorization in Overparameterized Autoencoders

Mikhail Belkin, Caroline Uhler, Adityanarayanan Radhakrishnan, 2018 .

Towards a Theoretical Foundation for Laplacian-Based Manifold Methods

Mikhail Belkin, Partha Niyogi, 2005, COLT.

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

Mikhail Belkin, Hariharan Narayanan, Partha Niyogi, 2013, Random Struct. Algorithms.

Learning with Fredholm Kernels

Mikhail Belkin, Yusu Wang, Qichao Que, 2014, NIPS.

Eigenvectors of Orthogonally Decomposable Functions

Mikhail Belkin, Luis Rademacher, James R. Voss, 2014, SIAM J. Comput..

Polynomial Learning of Distribution Families

Mikhail Belkin, Kaushik Sinha, Mikhail Belkin, 2010, 2010 IEEE 51st Annual Symposium on Foundations of Computer Science.

Constructing Laplace operator from point clouds in Rd

Mikhail Belkin, Yusu Wang, Jian Sun, 2009, SODA.

Blind Signal Separation in the Presence of Gaussian Noise

Mikhail Belkin, Luis Rademacher, James R. Voss, 2012, COLT.

Data Skeletonization via Reeb Graphs

Mikhail Belkin, Yusu Wang, Issam Safa, 2011, NIPS.

Probabilistic Zero-shot Classification with Semantic Rankings pdf

Mikhail Belkin, Jihun Hamm, Mikhail Belkin, 2015, ArXiv.

Probabilistic mixtures of differential profiles for shape recognition

Mikhail Belkin, Lei Ding, 2008, 2008 19th International Conference on Pattern Recognition.

Semi-Supervised Learning

Mikhail Belkin, Xueyuan Zhou, Mikhail Belkin, 2021, Machine Learning.

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

Mikhail Belkin, Siyuan Ma, Mikhail Belkin, 2017, NIPS.

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

Mikhail Belkin, Hariharan Narayanan, Partha Niyogi, 2006, NIPS.

Appreciation to IJCV Reviewers

Mikhail Belkin, Adrian Barbu, Xiang Bai, 2013, International Journal of Computer Vision.

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

Mikhail Belkin, Dong Xuan, Adam C. Champion, 2015, 2015 IEEE 35th International Conference on Distributed Computing Systems.

Networks of Memories

Mikhail Belkin, Simon Dennis, 2013 .

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

Mikhail Belkin, Anant Sahai, Vignesh Subramanian, 2020, ArXiv.

Reconciling modern machine-learning practice and the classical bias–variance trade-off

Mikhail Belkin, Daniel J. Hsu, Daniel Hsu, 2018, Proceedings of the National Academy of Sciences.

Learning Gaussian Mixtures with Arbitrary Separation pdf

Mikhail Belkin, Kaushik Sinha, Mikhail Belkin, 2009, ArXiv.

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

Mikhail Belkin, Libin Zhu, Chaoyue Liu, 2020, NeurIPS.

Laplacian Eigenmaps for Dimensionality Reduction and Data Representation

Mikhail Belkin, Partha Niyogi, Mikhail Belkin, 2003, Neural Computation.

Fast Algorithms for Gaussian Noise Invariant Independent Component Analysis

Mikhail Belkin, Luis Rademacher, James R. Voss, 2013, NIPS.

Learning speaker normalization using semisupervised manifold alignment

Mikhail Belkin, Eric Fosler-Lussier, Mary E. Beckman, 2010, INTERSPEECH.

Laplacian Support Vector Machines Trained in the Primal

Mikhail Belkin, Stefano Melacci, Mikhail Belkin, 2009, J. Mach. Learn. Res..

Heat Flow and a Faster Algorithm to Compute the Surface Area of a Convex Body

Mikhail Belkin, Hariharan Narayanan, Partha Niyogi, 2006, 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06).

Beyond Hartigan Consistency: Merge Distortion Metric for Hierarchical Clustering

Mikhail Belkin, Yusu Wang, Justin Eldridge, 2015, COLT.

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

Ulrike von Luxburg, Mikhail Belkin, Olivier Bousquet, 2004, COLT.

Robust features for the automatic identification of autism spectrum disorder in children

Mikhail Belkin, Justin Eldridge, Alison E Lane, 2014, Journal of Neurodevelopmental Disorders.

Towards a theoretical foundation for Laplacian-based manifold methods

Mikhail Belkin, Partha Niyogi, Mikhail Belkin, 2005, J. Comput. Syst. Sci..

Parametrized Accelerated Methods Free of Condition Number pdf

Mikhail Belkin, Chaoyue Liu, Chaoyue Liu, 2018, ArXiv.

Kernel Machines That Adapt To Gpus For Effective Large Batch Training

Mikhail Belkin, Siyuan Ma, Mikhail Belkin, 2018, SysML.

Limits of Spectral Clustering

Ulrike von Luxburg, Mikhail Belkin, Olivier Bousquet, 2004, NIPS.

Discrete laplace operator on meshed surfaces

Mikhail Belkin, Yusu Wang, Jian Sun, 2008, SCG '08.

Component based shape retrieval using differential profiles

Mikhail Belkin, Lei Ding, Mikhail Belkin, 2008, MIR '08.

Maximum Margin Semi-Supervised Learning for Structured Variables

Mikhail Belkin, Yasemin Altun, David A. McAllester, 2005, NIPS 2005.

Fast Interactive Image Retrieval using large-scale unlabeled data pdf

Mikhail Belkin, Jihun Hamm, Akshay Mehra, 2018, ArXiv.

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

Mikhail Belkin, Siyuan Ma, Soumik Mandal, 2018, ArXiv.

Two models of double descent for weak features

Mikhail Belkin, Ji Xu, Daniel J. Hsu, 2019, SIAM J. Math. Data Sci..

Multiple Descent: Design Your Own Generalization Curve pdf

Amin Karbasi, Mikhail Belkin, Lin Chen, 2020, NeurIPS.

A Note on Learning with Integral Operators

Mikhail Belkin, Lorenzo Rosasco, Ernesto De Vito, 2009, COLT.

Downsampling leads to Image Memorization in Convolutional Autoencoders pdf

Mikhail Belkin, Caroline Uhler, Adityanarayanan Radhakrishnan, 2018, ArXiv.

Overparameterized Neural Networks Can Implement Associative Memory pdf

Mikhail Belkin, Caroline Uhler, Adityanarayanan Radhakrishnan, 2019, ArXiv.

Using eigenvectors of the bigram graph to infer morpheme identity

Mikhail Belkin, John A. Goldsmith, 2002, SIGMORPHON.

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

Raef Bassily, Mikhail Belkin, Siyuan Ma, 2017, ICML.

Regularization and Semi-supervised Learning on Large Graphs

Mikhail Belkin, Partha Niyogi, Irina Matveeva, 2004, COLT.

Metric Based Automatic Event Segmentation

Mikhail Belkin, Simon Dennis, Yuwen Zhuang, 2012, MobiCASE.

Kernel Machines Beat Deep Neural Networks on Mask-based Single-channel Speech Enhancement

Mikhail Belkin, Siyuan Ma, Like Hui, 2019, INTERSPEECH.

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

Mikhail Belkin, Vikas Sindhwani, Partha Niyogi, 2005, ICML.

Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks pdf

Mikhail Belkin, Like Hui, 2020, ArXiv.

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

Mikhail Belkin, Kaushik Sinha, 2007, NIPS.

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

Mikhail Belkin, Quanquan Gu, Yuan Cao, 2021, NeurIPS.

Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks pdf

Mikhail Belkin, Like Hui, Mikhail Belkin, 2020, ICLR.

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

Mikhail Belkin, Caroline Uhler, Adityanarayanan Radhakrishnan, 2021, Proceedings of the National Academy of Sciences of the United States of America.

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

Mikhail Belkin, Mikhail Belkin, M. Belkin, 2021, Acta Numerica.

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

Mikhail Belkin, Caroline Uhler, Adityanarayanan Radhakrishnan, 2021, ArXiv.

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

Mikhail Belkin, Anant Sahai, Daniel J. Hsu, 2020, J. Mach. Learn. Res..

The network properties of episodic graphs

Mikhail Belkin, Simon Dennis, Yuwen Zhuang, 2010 .

Using eigenvectors of the bigram graph to infer grammatical features and categories

Mikhail Belkin, John Goldsmith, 2002 .

Topological Data Analysis and Machine Learning Theory

Sayan Mukherjee, Mikhail Belkin, Brittany Terese Fasy, 2012 .

The Geometry and Dynamics of Lifelogs: Discovering the Organizational Principles of Human Experience

Mikhail Belkin, Simon Dennis, Yuwen Zhuang, 2014, PloS one.

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

Mikhail Belkin, Chaoyue Liu, Mikhail Belkin, 2020, NeurIPS.

Denali : A tool for visualizing scalar functions as landscape metaphors

Mikhail Belkin, Justin Eldridge, Yusu Wang, 2014 .

Multiple Descent: Design Your Own Generalization Curve pdf

Amin Karbasi, Mikhail Belkin, Yifei Min, 2020, NeurIPS.