Tomas Vaskevicius

5 papers · 2019–2024 · 3 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 ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird

Venues

NeurIPS (3) COLT (1) JMLR (1)

Top co-authors

Varun Kanade (3) Patrick Rebeschini (3) Nikita Zhivotovskiy (1) Lénaïc Chizat (1) Jaouad Mourtada (1)

Research topics

Machine Learning (4) Optimization & Theory · Machine Learning (4) Mathematics & Optimization (3) Optimization (3) Deep Learning (2) Optimization & Theory · Deep Learning (2) Artificial Intelligence (1) Bayesian & Probabilistic (1) Core Methods (1) Learning Types (1) Mathematics (1)

Keywords

implicit regularization (2) compressed sensing (1) model selection (1) optimal transport (1) empirical risk minimization (1) signal reconstruction (1) gradient descent (1) deviation bounds (1) excess risk (1) least squares regression (1) mirror descent (1) excess risk bound (1) early stopping (1) local rademacher complexity (1) entropic regularization (1) statistical aggregation (1) convergence guarantee (1) pac-bayes bound (1) minimax rate (1) risk bound (1)

Papers

Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition JMLR 2024 Computational Guarantees for Doubly Entropic Wasserstein Barycenters NeurIPS 2023 Local Risk Bounds for Statistical Aggregation COLT 2023 The Statistical Complexity of Early-Stopped Mirror Descent NeurIPS 2020 Implicit Regularization for Optimal Sparse Recovery NeurIPS 2019