Sankar, Lalitha

15 publications

NeurIPS 2025 CORAL: Disentangling Latent Representations in Long-Tailed Diffusion Esther Rodriguez, Monica Welfert, Samuel McDowell, Nathan Stromberg, Julian Antolin Camarena, Lalitha Sankar

TMLR 2025 Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates Daniil Vankov, Angelia Nedich, Lalitha Sankar

NeurIPS 2025 GeoClip: Geometry-Aware Clipping for Differentially Private SGD Atefeh Gilani, Naima Tasnim, Lalitha Sankar, Oliver Kosut

ICLR 2025 Optimizing $(l_0, L_1)$-Smooth Functions by Gradient Methods Daniil Vankov, Anton Rodomanov, Angelia Nedich, Lalitha Sankar, Sebastian U Stich

ICML 2025 Optimizing Noise Distributions for Differential Privacy Atefeh Gilani, Juan Felipe Gomez, Shahab Asoodeh, Flavio Calmon, Oliver Kosut, Lalitha Sankar

TMLR 2025 Robust Model Selection of Gaussian Graphical Models Abrar Zahin, Rajasekhar Anguluri, Lalitha Sankar, Oliver Kosut, Gautam Dasarathy

NeurIPS 2025 Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Nathan Stromberg, Christos Thrampoulidis, Lalitha Sankar

NeurIPS 2024 Enhancing Robustness of Last Layer Two-Stage Fair Model Corrections Nathan Stromberg, Rohan Ayyagari, Sanmi Koyejo, Richard Nock, Lalitha Sankar

TMLR 2024 For Robust Worst-Group Accuracy, Ignore Group Annotations Nathan Stromberg, Rohan Ayyagari, Monica Welfert, Sanmi Koyejo, Richard Nock, Lalitha Sankar

ICML 2024 Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes Daniil Vankov, Angelia Nedich, Lalitha Sankar

NeurIPSW 2023 Last Iterate Convergence of Popov Method for Non-Monotone Stochastic Variational Inequalities Daniil Vankov, Angelia Nedich, Lalitha Sankar

AISTATS 2023 Smoothly Giving up: Robustness for Simple Models Tyler Sypherd, Nathaniel Stromberg, Richard Nock, Visar Berisha, Lalitha Sankar

ICML 2023 The Saddle-Point Method in Differential Privacy Wael Alghamdi, Juan Felipe Gomez, Shahab Asoodeh, Flavio Calmon, Oliver Kosut, Lalitha Sankar

ICMLW 2023 Tunable Dual-Objective GANs for Stable Training Monica Welfert, Kyle Otstot, Gowtham Raghunath Kurri, Lalitha Sankar

ICML 2022 Being Properly Improper Tyler Sypherd, Richard Nock, Lalitha Sankar