Matus Telgarsky
26 papers · 2010–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🗺️ Taxonomy Completionist (29) 🏃 Academic Marathon · Full 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(13)
🏆
Keyword Champion
(2)
🌈
Renaissance Researcher
(5)
📈
Trend Setter
🚀
Conference Pioneer
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(108)
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(26)
Optimization & Theory · Machine Learning
(24)
Core Methods
(9)
Deep Learning
(7)
Mathematics & Optimization
(4)
Learning Types
(4)
Optimization
(4)
Optimization & Theory · Deep Learning
(4)
Artificial Intelligence
(3)
Architectures
(3)
Core AI
(3)
Computer Science
(1)
Data Science & Analytics
(1)
Reinforcement Learning
(1)
Applications
(1)
Keywords
gradient descent
(7)
implicit bia
(4)
maximum margin
(4)
empirical risk minimization
(4)
implicit regularization
(3)
convergence rate
(3)
generalization bound
(3)
neural tangent kernel
(3)
mirror descent
(3)
convex optimization
(3)
stochastic gradient descent
(3)
logistic loss
(3)
relu network
(3)
stochastic optimization
(2)
logistic regression
(2)
margin maximization
(2)
adversarial robustness
(2)
optimal transport
(2)
sample complexity
(2)
dual optimization
(2)
Papers
Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
ICML 2025
Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency
COLT 2024
Spectrum Extraction and Clipping for Implicitly Linear Layers
AISTATS 2024
Transformers, parallel computation, and logarithmic depth
ICML 2024
Feature selection and low test error in shallow low-rotation ReLU networks
ICLR 2023
On Achieving Optimal Adversarial Test Error
ICLR 2023
Actor-critic is implicitly biased towards high entropy optimal policies
ICLR 2022
Stochastic linear optimization never overfits with quadratically-bounded losses on general data
COLT 2022
Characterizing the implicit bias via a primal-dual analysis
ALT 2021
Fast margin maximization via dual acceleration
ICML 2021
Generalization bounds via distillation
ICLR 2021
Gradient descent follows the regularization path for general losses
COLT 2020
Neural tangent kernels, transportation mappings, and universal approximation
ICLR 2020
Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks
ICLR 2020
A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization
ICML 2019
Gradient descent aligns the layers of deep linear networks
ICLR 2019
The implicit bias of gradient descent on nonseparable data
COLT 2019
Neural Networks and Rational Functions
ICML 2017
Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
COLT 2017
benefits of depth in neural networks
COLT 2016
Convex Risk Minimization and Conditional Probability Estimation
COLT 2015
Tensor Decompositions for Learning Latent Variable Models
JMLR 2014
Boosting with the Logistic Loss is Consistent
COLT 2013
Margins, Shrinkage, and Boosting
ICML 2013
A Primal-Dual Convergence Analysis of Boosting
JMLR 2012
Hartigan’s Method: k-means Clustering without Voronoi
AISTATS 2010