Lalitha Sankar

7 papers · 2022–2025 · 4 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 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14)

Venues

ICML (4) AISTATS (1) ICLR (1) NeurIPS (1)

Top co-authors

Richard Nock (3) Juan Felipe Gomez (2) Oliver Kosut (2) Tyler Sypherd (2) Flavio Calmon (2) Daniil Vankov (2) Angelia Nedich (2) Shahab Asoodeh (2) Atefeh Gilani (1) Rohan Ayyagari (1)

Research topics

Machine Learning (7) Optimization & Theory (6) Mathematics & Optimization (4) Optimization (3) Artificial Intelligence (2) Application Areas (2) Core AI (2) Core Methods (2) Learning Types (2) Security & Privacy (1) Differential Privacy (1) Mathematics (1) Probability (1)

Keywords

non-convex optimization (2) label noise (2) differential privacy (2) posterior distribution (1) gradient descent (1) variance (1) boosting algorithm (1) convergence rate (1) loss function (1) generalized smoothness (1) adaptive step size (1) proper loss (1) privacy accounting (1) margin-based loss (1) robust training (1) worst-group accuracy (1) noise distribution (1) accelerated gradient method (1) projection method (1) subgroup fairness (1)

Papers

Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods ICLR 2025 Optimizing Noise Distributions for Differential Privacy ICML 2025 Enhancing Robustness of Last Layer Two-Stage Fair Model Corrections NeurIPS 2024 Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes ICML 2024 Smoothly Giving up: Robustness for Simple Models AISTATS 2023 The Saddle-Point Method in Differential Privacy ICML 2023 Being Properly Improper ICML 2022