Mikhail Belkin

171 papers A* 42A 9B 2Journal 92Unranked 26

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing. CoRR Parsa Mirtaheri, Mikhail Belkin
2026	J	`jnl`	General and Efficient Steering of Unconditional Diffusion. CoRR Qingsong Wang, Mikhail Belkin, Yusu Wang
2025	A*	`conf`	A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis. COLT Akash Kumar, Rahul Parhi, Mikhail Belkin
2025	J	`jnl`	A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis. CoRR Akash Kumar, Rahul Parhi, Mikhail Belkin
2025	J	`jnl`	Aggregate and conquer: detecting and steering LLM concepts by combining nonlinear predictors over multiple layers. CoRR Daniel Beaglehole, Adityanarayanan Radhakrishnan, Enric Boix-Adserà, Mikhail Belkin
2025	A*	`conf`	Emergence in non-neural models: grokking modular arithmetic via average gradient outer product. ICML Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin
2025	J	`jnl`	FACT: the Features At Convergence Theorem for neural networks. CoRR Enric Boix-Adserà, Neil Mallinar, James B. Simon, Mikhail Belkin
2025	J	`jnl`	Task Generalization With AutoRegressive Compositional Structure: Can Learning From CoRR Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen, Hongzhou Lin, Jingzhao Zhang, Mikhail Belkin
2025	A*	`conf`	Task Generalization with Autoregressive Compositional Structure: Can Learning from D Tasks Generalize to DT Tasks? ICML Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen, Hongzhou Lin, Jingzhao Zhang, Mikhail Belkin
2025	—	`conf`	UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models. NAACL (Long Papers) Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, Ramón Huerta, Ivan Vulic
2025	J	`jnl`	xRFM: Accurate, scalable, and interpretable feature learning models for tabular data. CoRR Daniel Beaglehole, David Holzmüller, Adityanarayanan Radhakrishnan, Mikhail Belkin
2024	A*	`conf`	Average gradient outer product as a mechanism for deep neural collapse. NeurIPS Daniel Beaglehole, Peter Súkeník, Marco Mondelli, Mikhail Belkin
2024	J	`jnl`	Average gradient outer product as a mechanism for deep neural collapse. CoRR Daniel Beaglehole, Peter Súkeník, Marco Mondelli, Mikhail Belkin
2024	A*	`conf`	Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning. ICML Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2024	J	`jnl`	Context-Scaling versus Task-Scaling in In-Context Learning. CoRR Amirhesam Abedsoltan, Adityanarayanan Radhakrishnan, Jingfeng Wu, Mikhail Belkin
2024	J	`jnl`	Emergence in non-neural models: grokking modular arithmetic via average gradient outer product. CoRR Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin
2024	J	`jnl`	Fast training of large kernel models with delayed projections. CoRR Amirhesam Abedsoltan, Siyuan Ma, Parthe Pandit, Mikhail Belkin
2024	J	`jnl`	Linear Recursive Feature Machines provably recover low-rank matrices. CoRR Adityanarayanan Radhakrishnan, Mikhail Belkin, Dmitriy Drusvyatskiy
2024	J	`jnl`	Mirror Descent on Reproducing Kernel Banach Spaces. CoRR Akash Kumar, Mikhail Belkin, Parthe Pandit
2024	A*	`conf`	More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory. ICLR James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin
2024	A	`conf`	On the Nyström Approximation for Preconditioning in Kernel Machines. AISTATS Amirhesam Abedsoltan, Parthe Pandit, Luis Rademacher, Mikhail Belkin
2024	A*	`conf`	Quadratic models for understanding catapult dynamics of neural networks. ICLR Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2024	A	`conf`	Uncertainty Estimation with Recursive Feature Machines. UAI Daniel Gedon, Amirhesam Abedsoltan, Thomas B. Schön, Mikhail Belkin
2024	J	`jnl`	Unmemorization in Large Language Models via Self-Distillation and Deliberate Imagination. CoRR Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, Ramón Huerta, Ivan Vulic
2023	J	`jnl`	A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors. SIAM J. Math. Data Sci. Nikhil Ghosh, Mikhail Belkin
2023	A*	`conf`	Aiming towards the minimizers: fast convergence of SGD for overparametrized problems. NeurIPS Chaoyue Liu, Dmitriy Drusvyatskiy, Mikhail Belkin, Damek Davis, Yi-An Ma
2023	J	`jnl`	Aiming towards the minimizers: fast convergence of SGD for overparametrized problems. CoRR Chaoyue Liu, Dmitriy Drusvyatskiy, Mikhail Belkin, Damek Davis, Yi-An Ma
2023	J	`jnl`	Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning. CoRR Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2023	A*	`conf`	Cut your Losses with Squentropy. ICML Like Hui, Mikhail Belkin, Stephen Wright
2023	J	`jnl`	Cut your Losses with Squentropy. CoRR Like Hui, Mikhail Belkin, Stephen Wright
2023	J	`jnl`	Mechanism of feature learning in convolutional neural networks. CoRR Daniel Beaglehole, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin
2023	J	`jnl`	More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory. CoRR James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin
2023	A	`conf`	Neural tangent kernel at initialization: linear width suffices. UAI Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2023	J	`jnl`	On Emergence of Clean-Priority Learning in Early Stopped Neural Networks. CoRR Chaoyue Liu, Amirhesam Abedsoltan, Mikhail Belkin
2023	J	`jnl`	On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions. SIAM J. Math. Data Sci. Daniel Beaglehole, Mikhail Belkin, Parthe Pandit
2023	J	`jnl`	On the Nystrom Approximation for Preconditioning in Kernel Machines. CoRR Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit, Luis Rademacher
2023	A*	`conf`	Restricted Strong Convexity of Deep Learning Models with Smooth Activations. ICLR Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2023	A*	`conf`	Toward Large Kernel Models. ICML Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit
2023	J	`jnl`	Toward Large Kernel Models. CoRR Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit
2022	J	`jnl`	A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors. CoRR Nikhil Ghosh, Mikhail Belkin
2022	J	`jnl`	A note on Linear Bottleneck networks and their Transition to Multilinearity. CoRR Libin Zhu, Parthe Pandit, Mikhail Belkin
2022	J	`jnl`	Benign Overfitting in Two-layer Convolutional Neural Networks. CoRR Yuan Cao, Zixiang Chen, Mikhail Belkin, Quanquan Gu
2022	J	`jnl`	Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting. CoRR Neil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit, Mikhail Belkin, Preetum Nakkiran
2022	A*	`conf`	Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting. NeurIPS Neil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit, Mikhail Belkin, Preetum Nakkiran
2022	J	`jnl`	Feature learning in neural networks and kernel machines that recursively learn features. CoRR Adityanarayanan Radhakrishnan, Daniel Beaglehole, Parthe Pandit, Mikhail Belkin
2022	J	`jnl`	Kernel Ridgeless Regression is Inconsistent for Low Dimensions. CoRR Daniel Beaglehole, Mikhail Belkin, Parthe Pandit
2022	J	`jnl`	Limitations of Neural Collapse for Understanding Generalization in Deep Learning. CoRR Like Hui, Mikhail Belkin, Preetum Nakkiran
2022	J	`jnl`	Quadratic models for understanding neural network dynamics. CoRR Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2022	J	`jnl`	Restricted Strong Convexity of Deep Learning Models with Smooth Activations. CoRR Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2022	A*	`conf`	Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture. NeurIPS Libin Zhu, Chaoyue Liu, Mikhail Belkin
2022	J	`jnl`	Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture. CoRR Libin Zhu, Chaoyue Liu, Mikhail Belkin
2022	A*	`conf`	Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models. ICLR Chaoyue Liu, Libin Zhu, Mikhail Belkin
2022	J	`jnl`	Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models. CoRR Chaoyue Liu, Libin Zhu, Mikhail Belkin
2022	J	`jnl`	Wide and Deep Neural Networks Achieve Optimality for Classification. CoRR Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
2021	J	`jnl`	Classification vs regression in overparameterized regimes: Does the loss function matter? J. Mach. Learn. Res. Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin, Daniel Hsu, Anant Sahai
2021	A*	`ed.`	Conference on Learning Theory, COLT 2021, 15-19 August 2021, Boulder, Colorado, USA. COLT Mikhail Belkin, Samory Kpotufe
2021	A*	`conf`	Evaluation of Neural Architectures trained with square Loss vs Cross-Entropy in Classification Tasks. ICLR Like Hui, Mikhail Belkin
2021	J	`jnl`	Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation. Acta Numer. Mikhail Belkin
2021	J	`jnl`	Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation. CoRR Mikhail Belkin
2021	J	`jnl`	Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size. CoRR Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
2021	A*	`conf`	Multiple Descent: Design Your Own Generalization Curve. NeurIPS Lin Chen, Yifei Min, Mikhail Belkin, Amin Karbasi
2021	A*	`conf`	Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures. NeurIPS Yuan Cao, Quanquan Gu, Mikhail Belkin
2021	J	`jnl`	Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures. CoRR Yuan Cao, Quanquan Gu, Mikhail Belkin
2021	J	`jnl`	Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks. CoRR Adityanarayanan Radhakrishnan, George Stefanakis, Mikhail Belkin, Caroline Uhler
2020	A*	`conf`	Accelerating SGD with momentum for over-parameterized learning. ICLR Chaoyue Liu, Mikhail Belkin
2020	J	`jnl`	Back to the Future: Radial Basis Function Network Revisited. IEEE Trans. Pattern Anal. Mach. Intell. Qichao Que, Mikhail Belkin
2020	J	`jnl`	Classification vs regression in overparameterized regimes: Does the loss function matter? CoRR Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin, Daniel J. Hsu, Anant Sahai
2020	J	`jnl`	Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks. CoRR Like Hui, Mikhail Belkin
2020	J	`jnl`	Linear Convergence and Implicit Regularization of Generalized Mirror Descent with Time-Dependent Mirrors. CoRR Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
2020	J	`jnl`	Multiple Descent: Design Your Own Generalization Curve. CoRR Lin Chen, Yifei Min, Mikhail Belkin, Amin Karbasi
2020	A*	`conf`	On the linearity of large non-linear models: when and why the tangent kernel is constant. NeurIPS Chaoyue Liu, Libin Zhu, Mikhail Belkin
2020	J	`jnl`	On the linearity of large non-linear models: when and why the tangent kernel is constant. CoRR Chaoyue Liu, Libin Zhu, Mikhail Belkin
2020	J	`jnl`	Overparameterized neural networks implement associative memory. Proc. Natl. Acad. Sci. USA Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
2020	J	`jnl`	Toward a theory of optimization for over-parameterized systems of non-linear equations: the lessons of deep learning. CoRR Chaoyue Liu, Libin Zhu, Mikhail Belkin
2020	J	`jnl`	Two Models of Double Descent for Weak Features. SIAM J. Math. Data Sci. Mikhail Belkin, Daniel Hsu, Ji Xu
2019	A	`conf`	Does data interpolation contradict statistical optimality? AISTATS Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov
2019	A	`conf`	Kernel Machines Beat Deep Neural Networks on Mask-Based Single-Channel Speech Enhancement. INTERSPEECH Like Hui, Siyuan Ma, Mikhail Belkin
2019	—	`conf`	Kernel Machines That Adapt To Gpus For Effective Large Batch Training. SysML Siyuan Ma, Mikhail Belkin
2019	J	`jnl`	Overparameterized Neural Networks Can Implement Associative Memory. CoRR Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
2019	J	`jnl`	Two models of double descent for weak features. CoRR Mikhail Belkin, Daniel Hsu, Ji Xu
2018	A*	`conf`	Approximation beats concentration? An approximation view on inference with smooth radial kernels. COLT Mikhail Belkin
2018	J	`jnl`	Approximation beats concentration? An approximation view on inference with smooth radial kernels. CoRR Mikhail Belkin
2018	J	`jnl`	Does data interpolation contradict statistical optimality? CoRR Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov
2018	J	`jnl`	Downsampling leads to Image Memorization in Convolutional Autoencoders. CoRR Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
2018	J	`jnl`	Eigenvectors of Orthogonally Decomposable Functions. SIAM J. Comput. Mikhail Belkin, Luis Rademacher, James R. Voss
2018	J	`jnl`	Fast Interactive Image Retrieval using large-scale unlabeled data. CoRR Akshay Mehra, Jihun Hamm, Mikhail Belkin
2018	J	`jnl`	Kernel Machines Beat Deep Neural Networks on Mask-based Single-channel Speech Enhancement. CoRR Like Hui, Siyuan Ma, Mikhail Belkin
2018	J	`jnl`	Learning kernels that adapt to GPU. CoRR Siyuan Ma, Mikhail Belkin
2018	J	`jnl`	MaSS: an Accelerated Stochastic Method for Over-parametrized Learning. CoRR Chaoyue Liu, Mikhail Belkin
2018	J	`jnl`	On exponential convergence of SGD in non-convex over-parametrized learning. CoRR Raef Bassily, Mikhail Belkin, Siyuan Ma
2018	A*	`conf`	Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate. NeurIPS Mikhail Belkin, Daniel J. Hsu, Partha Mitra
2018	J	`jnl`	Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate. CoRR Mikhail Belkin, Daniel Hsu, Partha Mitra
2018	J	`jnl`	Parametrized Accelerated Methods Free of Condition Number. CoRR Chaoyue Liu, Mikhail Belkin
2018	J	`jnl`	Reconciling modern machine learning and the bias-variance trade-off. CoRR Mikhail Belkin, Daniel Hsu, Siyuan Ma, Soumik Mandal
2018	A*	`conf`	The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning. ICML Siyuan Ma, Raef Bassily, Mikhail Belkin
2018	A*	`conf`	To Understand Deep Learning We Need to Understand Kernel Learning. ICML Mikhail Belkin, Siyuan Ma, Soumik Mandal
2018	J	`jnl`	To understand deep learning we need to understand kernel learning. CoRR Mikhail Belkin, Siyuan Ma, Soumik Mandal
2018	B	`conf`	Unperturbed: spectral analysis beyond Davis-Kahan. ALT Justin Eldridge, Mikhail Belkin, Yusu Wang
2017	—	`conf`	Diving into the shallows: a computational perspective on large-scale shallow learning. NIPS Siyuan Ma, Mikhail Belkin
2017	J	`jnl`	Diving into the shallows: a computational perspective on large-scale shallow learning. CoRR Siyuan Ma, Mikhail Belkin
2017	J	`jnl`	The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning. CoRR Siyuan Ma, Raef Bassily, Mikhail Belkin
2017	J	`jnl`	Unperturbed: spectral analysis beyond Davis-Kahan. CoRR Justin Eldridge, Mikhail Belkin, Yusu Wang
2016	A	`conf`	Back to the Future: Radial Basis Function Networks Revisited. AISTATS Qichao Que, Mikhail Belkin
2016	A*	`conf`	Basis Learning as an Algorithmic Primitive. COLT Mikhail Belkin, Luis Rademacher, James R. Voss
2016	—	`conf`	Clustering with Bregman Divergences: an Asymptotic Analysis. NIPS Chaoyue Liu, Mikhail Belkin
2016	—	`conf`	Graphons, mergeons, and so on! NIPS Justin Eldridge, Mikhail Belkin, Yusu Wang
2016	J	`jnl`	Graphons, mergeons, and so on! CoRR Justin Eldridge, Mikhail Belkin, Yusu Wang
2016	J	`jnl`	Learning Privately from Multiparty Data. CoRR Jihun Hamm, Paul Cao, Mikhail Belkin
2016	A*	`conf`	Learning privately from multiparty data. ICML Jihun Hamm, Yingjun Cao, Mikhail Belkin
2016	A*	`conf`	The Hidden Convexity of Spectral Clustering. AAAI James R. Voss, Mikhail Belkin, Luis Rademacher
2015	—	`conf`	A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA. NIPS James R. Voss, Mikhail Belkin, Luis Rademacher
2015	A*	`conf`	Beyond Hartigan Consistency: Merge Distortion Metric for Hierarchical Clustering. COLT Justin Eldridge, Mikhail Belkin, Yusu Wang
2015	A	`conf`	Crowd-ML: A Privacy-Preserving Learning Framework for a Crowd of Smart Devices. ICDCS Jihun Hamm, Adam C. Champion, Guoxing Chen, Mikhail Belkin, Dong Xuan
2015	J	`jnl`	Crowd-ML: A Privacy-Preserving Learning Framework for a Crowd of Smart Devices. CoRR Jihun Hamm, Adam C. Champion, Guoxing Chen, Mikhail Belkin, Dong Xuan
2015	—	`conf`	Microwave-Band Circuit-Level Semiconductor Laser Modeling. EMS Mikhail Belkin, Vladimir Iakovlev
2015	J	`jnl`	Optimal Recovery in Noisy ICA. CoRR James R. Voss, Mikhail Belkin, Luis Rademacher
2015	J	`jnl`	Polynomial Learning of Distribution Families. SIAM J. Comput. Mikhail Belkin, Kaushik Sinha
2015	J	`jnl`	Probabilistic Zero-shot Classification with Semantic Rankings. CoRR Jihun Hamm, Mikhail Belkin
2014	J	`jnl`	Learning a Hidden Basis Through Imperfect Measurements: An Algorithmic Primitive. CoRR Mikhail Belkin, Luis Rademacher, James R. Voss
2014	—	`conf`	Learning with Fredholm Kernels. NIPS Qichao Que, Mikhail Belkin, Yusu Wang
2014	J	`jnl`	The Hidden Convexity of Spectral Clustering. CoRR Mikhail Belkin, Luis Rademacher, James R. Voss
2014	A*	`conf`	The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures. COLT Joseph Anderson, Mikhail Belkin, Navin Goyal, Luis Rademacher, James R. Voss
2013	A*	`conf`	Blind Signal Separation in the Presence of Gaussian Noise. COLT Mikhail Belkin, Luis Rademacher, James R. Voss
2013	—	`conf`	Fast Algorithms for Gaussian Noise Invariant Independent Component Analysis. NIPS James R. Voss, Luis Rademacher, Mikhail Belkin
2013	J	`jnl`	Heat flow and a faster algorithm to compute the surface area of a convex body. Random Struct. Algorithms Mikhail Belkin, Hariharan Narayanan, Partha Niyogi
2013	J	`jnl`	Inverse Density as an Inverse Problem: The Fredholm Equation Approach CoRR Qichao Que, Mikhail Belkin
2013	—	`conf`	Inverse Density as an Inverse Problem: the Fredholm Equation Approach. NIPS Qichao Que, Mikhail Belkin
2013	J	`jnl`	The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures. CoRR Joseph Anderson, Mikhail Belkin, Navin Goyal, Luis Rademacher, James R. Voss
2012	—	`conf`	Automatic Annotation of Daily Activity from Smartphone-Based Multisensory Streams. MobiCASE Jihun Hamm, Benjamin Stone, Mikhail Belkin, Simon Dennis
2012	J	`jnl`	Blind Signal Separation in the Presence of Gaussian Noise CoRR Mikhail Belkin, Luis Rademacher, James R. Voss
2012	J	`jnl`	Graph Laplacians on Singular Manifolds: Toward understanding complex spaces: graph Laplacians on manifolds with singularities and boundaries CoRR Mikhail Belkin, Qichao Que, Yusu Wang, Xueyuan Zhou
2012	—	`conf`	Metric Based Automatic Event Segmentation. MobiCASE Yuwen Zhuang, Mikhail Belkin, Simon Dennis
2012	A*	`conf`	Toward Understanding Complex Spaces: Graph Laplacians on Manifolds with Singularities and Boundaries. COLT Mikhail Belkin, Qichao Que, Yusu Wang, Xueyuan Zhou
2011	A*	`conf`	An iterated graph laplacian approach for ranking on manifolds. KDD Xueyuan Zhou, Mikhail Belkin, Nathan Srebro
2011	J	`jnl`	Behavior of Graph Laplacians on Manifolds with Boundary CoRR Xueyuan Zhou, Mikhail Belkin
2011	—	`conf`	Data Skeletonization via Reeb Graphs. NIPS Xiaoyin Ge, Issam Safa, Mikhail Belkin, Yusu Wang
2011	J	`jnl`	Laplacian Support Vector Machines Trained in the Primal. J. Mach. Learn. Res. Stefano Melacci, Mikhail Belkin
2011	A	`conf`	Semi-supervised Learning by Higher Order Regularization. AISTATS Xueyuan Zhou, Mikhail Belkin
2010	A	`conf`	Learning speaker normalization using semisupervised manifold alignment. INTERSPEECH Andrew R. Plummer, Mary E. Beckman, Mikhail Belkin, Eric Fosler-Lussier, Benjamin Munson
2010	J	`jnl`	On Learning with Integral Operators. J. Mach. Learn. Res. Lorenzo Rosasco, Mikhail Belkin, Ernesto De Vito
2010	J	`jnl`	Polynomial Learning of Distribution Families CoRR Mikhail Belkin, Kaushik Sinha
2010	A*	`conf`	Polynomial Learning of Distribution Families. FOCS Mikhail Belkin, Kaushik Sinha
2010	A*	`conf`	Toward Learning Gaussian Mixtures with Arbitrary Separation. COLT Mikhail Belkin, Kaushik Sinha
2009	A*	`conf`	A Note on Learning with Integral Operators. COLT Lorenzo Rosasco, Mikhail Belkin, Ernesto De Vito
2009	A*	`conf`	Constructing Laplace operator from point clouds in SODA Mikhail Belkin, Jian Sun, Yusu Wang
2009	J	`jnl`	Learning Gaussian Mixtures with Arbitrary Separation CoRR Mikhail Belkin, Kaushik Sinha
2009	—	`conf`	Semi-Supervised Learning Using Sparse Eigenfunction Bases. AAAI Fall Symposium: Manifold Learning and Its Applications Kaushik Sinha, Mikhail Belkin
2009	—	`conf`	Semi-supervised Learning using Sparse Eigenfunction Bases. NIPS Kaushik Sinha, Mikhail Belkin
2008	—	`conf`	Component based shape retrieval using differential profiles. Multimedia Information Retrieval Lei Ding, Mikhail Belkin
2008	A*	`conf`	Data spectroscopy: learning mixture models using eigenspaces of convolution operators. ICML Tao Shi, Mikhail Belkin, Bin Yu
2008	—	`conf`	Discrete laplace operator on meshed surfaces. SCG Mikhail Belkin, Jian Sun, Yusu Wang
2008	B	`conf`	Probabilistic mixtures of differential profiles for shape recognition. ICPR Lei Ding, Mikhail Belkin
2008	J	`jnl`	Towards a theoretical foundation for Laplacian-based manifold methods. J. Comput. Syst. Sci. Mikhail Belkin, Partha Niyogi
2007	—	`conf`	The Value of Labeled and Unlabeled Examples when the Model is Imperfect. NIPS Kaushik Sinha, Mikhail Belkin
2006	—	`conf`	Convergence of Laplacian Eigenmaps. NIPS Mikhail Belkin, Partha Niyogi
2006	A*	`conf`	Heat Flow and a Faster Algorithm to Compute the Surface Area of a Convex Body. FOCS Mikhail Belkin, Hariharan Narayanan, Partha Niyogi
2006	J	`jnl`	Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples. J. Mach. Learn. Res. Mikhail Belkin, Partha Niyogi, Vikas Sindhwani
2006	—	`conf`	On the Relation Between Low Density Separation, Spectral Clustering and Graph Cuts. NIPS Hariharan Narayanan, Mikhail Belkin, Partha Niyogi
2005	A*	`conf`	Beyond the point cloud: from transductive to semi-supervised learning. ICML Vikas Sindhwani, Partha Niyogi, Mikhail Belkin
2005	—	`conf`	Margin Semi-Supervised Learning for Structured Variables. NIPS Yasemin Altun, David A. McAllester, Mikhail Belkin
2005	A*	`conf`	Towards a Theoretical Foundation for Laplacian-Based Manifold Methods. COLT Mikhail Belkin, Partha Niyogi
2004	—	`conf`	Limits of Spectral Clustering. NIPS Ulrike von Luxburg, Olivier Bousquet, Mikhail Belkin
2004	A*	`conf`	On the Convergence of Spectral Clustering on Random Samples: The Normalized Case. COLT Ulrike von Luxburg, Olivier Bousquet, Mikhail Belkin
2004	A*	`conf`	Regularization and Semi-supervised Learning on Large Graphs. COLT Mikhail Belkin, Irina Matveeva, Partha Niyogi
2004	J	`jnl`	Semi-Supervised Learning on Riemannian Manifolds. Mach. Learn. Mikhail Belkin, Partha Niyogi
2004	—	`conf`	Tikhonov regularization and semi-supervised learning on large graphs. ICASSP (3) Mikhail Belkin, Irina Matveeva, Partha Niyogi
2003	J	`jnl`	Laplacian Eigenmaps for Dimensionality Reduction and Data Representation. Neural Comput. Mikhail Belkin, Partha Niyogi
2002	—	`conf`	Using Manifold Stucture for Partially Labeled Classification. NIPS Mikhail Belkin, Partha Niyogi
2002	J	`jnl`	Using eigenvectors of the bigram graph to infer morpheme identity CoRR Mikhail Belkin, John A. Goldsmith
2002	—	`conf`	Using eigenvectors of the bigram graph to infer morpheme identity. SIGMORPHON Mikhail Belkin, John A. Goldsmith
2001	—	`conf`	Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering. NIPS Mikhail Belkin, Partha Niyogi