Matus Telgarsky

发表

Duality and Data Dependence in Boosting / - eScholarship

Matus Telgarsky, 2013 .

Risk and parameter convergence of logistic regression pdf

Matus Telgarsky, Ziwei Ji, Matus Telgarsky, 2018, ArXiv.

A Primal-Dual Convergence Analysis of Boosting

Matus Telgarsky, Matus Telgarsky, 2011, J. Mach. Learn. Res..

Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks pdf

Matus Telgarsky, Ziwei Ji, 2020, ICLR.

A refined primal-dual analysis of the implicit bias pdf

Matus Telgarsky, Ziwei Ji, Matus Telgarsky, 2019, ArXiv.

Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT)

Anima Anandkumar, Matus Telgarsky, Sham M. Kakade, 2015, ALT.

Directional convergence and alignment in deep learning pdf

Matus Telgarsky, Ziwei Ji, 2020, NeurIPS.

Benefits of Depth in Neural Networks pdf

Matus Telgarsky, Matus Telgarsky, 2016, COLT.

Gradient descent follows the regularization path for general losses

Matus Telgarsky, Robert E. Schapire, Ziwei Ji, 2020, COLT.

Rate of Price Discovery in Iterative Combinatorial Auctions

Matus Telgarsky, Jacob D. Abernethy, Sébastien Lahaie, 2015, EC.

The Convergence Rate of AdaBoost and Friends pdf

Matus Telgarsky, Matus Telgarsky, 2011, ArXiv.

Boosting with the Logistic Loss is Consistent pdf

Matus Telgarsky, Matus Telgarsky, 2013, COLT.

The Fast Convergence of Boosting

Matus Telgarsky, 2011, NIPS.

Agglomerative Bregman Clustering

Sanjoy Dasgupta, Matus Telgarsky, S. Dasgupta, 2012, ICML.

Representation Benefits of Deep Feedforward Networks pdf

Matus Telgarsky, Matus Telgarsky, 2015, ArXiv.

Social Welfare and Profit Maximization from Revealed Preferences pdf

Ruta Mehta, Matus Telgarsky, Ziwei Ji, 2017, WINE.

Characterizing the implicit bias via a primal-dual analysis

Matus Telgarsky, Ziwei Ji, Ziwei Ji, 2019, ALT.

Size-Noise Tradeoffs in Generative Networks

Matus Telgarsky, Bolton Bailey, Matus Telgarsky, 2018, NeurIPS.

Moment-based Uniform Deviation Bounds for k-means and Friends

Sanjoy Dasgupta, Matus Telgarsky, S. Dasgupta, 2013, NIPS.

Hartigan's Method: k-means Clustering without Voronoi

Matus Telgarsky, Andrea Vattani, Matus Telgarsky, 2010, AISTATS.

Blackwell Approachability and Minimax Theory pdf

Matus Telgarsky, 2011, ArXiv.

Dirichlet draws are sparse with high probability pdf

Matus Telgarsky, 2013, ArXiv.

Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis

Matus Telgarsky, Maxim Raginsky, Alexander Rakhlin, 2017, COLT.

Greedy bi-criteria approximations for k-medians and k-means pdf

Matus Telgarsky, Daniel J. Hsu, 2016, ArXiv.

Neural Networks and Rational Functions pdf

Matus Telgarsky, Matus Telgarsky, 2017, ICML.

A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization pdf

Jian Peng, Matus Telgarsky, Chao Zhang, 2019, ICML.

Signal Decomposition using Multiscale Admixture Models

Matus Telgarsky, John D. Lafferty, J. Lafferty, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Convex Risk Minimization and Conditional Probability Estimation pdf

Miroslav Dudík, Matus Telgarsky, 2015, COLT.

Approximation power of random neural networks pdf

Matus Telgarsky, Ziwei Ji, Bolton Bailey, 2019, ArXiv.

Price Discovery in Subgradient Combinatorial Auctions

Jacob Abernethy, Matus Telgarsky, Sébastien Lahaie, 2015, AMMA 2015.

Statistical Consistency of Finite-dimensional Unregularized Linear Classification pdf

Matus Telgarsky, 2012, ArXiv.

Neural tangent kernels, transportation mappings, and universal approximation pdf

Matus Telgarsky, Ziwei Ji, Ruicheng Xian, 2020, ICLR.

Tensor decompositions for learning latent variable models pdf

Anima Anandkumar, Matus Telgarsky, Sham M. Kakade, 2012, J. Mach. Learn. Res..

Scalable Non-linear Learning with Adaptive Polynomial Expansions

John Langford, Matus Telgarsky, Alekh Agarwal, 2014, NIPS.

Spectrally-normalized margin bounds for neural networks

Matus Telgarsky, Peter L. Bartlett, Dylan J. Foster, 2017, NIPS.

Margins, Shrinkage, and Boosting

Matus Telgarsky, Matus Telgarsky, 2013, ICML.

The implicit bias of gradient descent on nonseparable data

Matus Telgarsky, Ziwei Ji, Matus Telgarsky, 2019, COLT.

Gradient descent aligns the layers of deep linear networks pdf

Matus Telgarsky, Ziwei Ji, Matus Telgarsky, 2018, ICLR.

Early-stopped neural networks are consistent pdf

Matus Telgarsky, Ziwei Ji, Justin D. Li, 2021, NeurIPS.

Fast Margin Maximization via Dual Acceleration pdf

Matus Telgarsky, Nathan Srebro, Ziwei Ji, 2021, ICML.

Actor-critic is implicitly biased towards high entropy optimal policies pdf

Matus Telgarsky, Yuzheng Hu, Ziwei Ji, 2021, ArXiv.

Generalization bounds via distillation pdf

Matus Telgarsky, Ziwei Ji, Daniel Hsu, 2021, ICLR.

Characterizing the implicit bias via a primal-dual analysis

Matus Telgarsky, Ziwei Ji, 2021, ALT.