Skip to content

Matus Telgarsky

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

26

Venues

6

Active years

2007–2025

Best venue rank

A*

Where they publish

Papers

26 indexed papers, newest first.

YearVenueTitleAuthors
2025ICMLBenefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression.Jingfeng Wu, Peter L. Bartlett, Matus Telgarsky, Bin Yu
2024AISTATSSpectrum Extraction and Clipping for Implicitly Linear Layers.Ali Ebrahimpour Boroojeny, Matus Telgarsky, Hari Sundaram
2024COLTLarge Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency.Jingfeng Wu, Peter L. Bartlett, Matus Telgarsky, Bin Yu
2024ICMLTransformers, parallel computation, and logarithmic depth.Clayton Sanford, Daniel Hsu, Matus Telgarsky
2023ICLROn Achieving Optimal Adversarial Test Error.Justin D. Li, Matus Telgarsky
2023ICLRFeature selection and low test error in shallow low-rotation ReLU networks.Matus Telgarsky
2022COLTStochastic linear optimization never overfits with quadratically-bounded losses on general data.Matus Telgarsky
2022ICLRActor-critic is implicitly biased towards high entropy optimal policies.Yuzheng Hu, Ziwei Ji, Matus Telgarsky
2021ALTCharacterizing the implicit bias via a primal-dual analysis.Ziwei Ji, Matus Telgarsky
2021ICLRGeneralization bounds via distillation.Daniel Hsu, Ziwei Ji, Matus Telgarsky, Lan Wang
2021ICMLFast margin maximization via dual acceleration.Ziwei Ji, Nathan Srebro, Matus Telgarsky
2020COLTGradient descent follows the regularization path for general losses.Ziwei Ji, Miroslav Dudk, Robert E. Schapire, Matus Telgarsky
2020ICLRPolylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks.Ziwei Ji, Matus Telgarsky
2020ICLRNeural tangent kernels, transportation mappings, and universal approximation.Ziwei Ji, Matus Telgarsky, Ruicheng Xian
2019COLTThe implicit bias of gradient descent on nonseparable data.Ziwei Ji, Matus Telgarsky
2019ICLRGradient descent aligns the layers of deep linear networks.Ziwei Ji, Matus Telgarsky
2019ICMLA Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization.Yucheng Chen, Matus Telgarsky, Chao Zhang, Bolton Bailey, Daniel Hsu, Jian Peng
2017COLTNon-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis.Maxim Raginsky, Alexander Rakhlin, Matus Telgarsky
2017ICMLNeural Networks and Rational Functions.Matus Telgarsky
2016COLTbenefits of depth in neural networks.Matus Telgarsky
2015ALTTensor Decompositions for Learning Latent Variable Models (A Survey for ALT).Anima Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade, Matus Telgarsky
2015COLTConvex Risk Minimization and Conditional Probability Estimation.Matus Telgarsky, Miroslav Dudk
2013COLTBoosting with the Logistic Loss is Consistent.Matus Telgarsky
2013ICMLMargins, Shrinkage, and Boosting.Matus Telgarsky
2012ICMLAgglomerative Bregman Clustering.Matus Telgarsky, Sanjoy Dasgupta
2007ICASSPSignal Decomposition using Multiscale Admixture Models.Matus Telgarsky, John D. Lafferty