activity
20242026
most citedNonconvex-Nonconcave Min-Max Optimization with a Small Maximization Domain

4 citations · 4 across the 1 of their papers we have counts for

collaborators

20 papers

math.OC20264 cited

Nonconvex-Nonconcave Min-Max Optimization with a Small Maximization Domain

Dmitrii M. Ostrovskii, Babak Barazandeh, Meisam Razaviyayn

We study the problem of finding approximate first-order stationary points in optimization problems of the form , where the sets are conv…

cs.LG2026

Efficient DP-SGD for LLMs with Randomized Clipping

Enayat Ullah, Sai Aparna Aketi, Devansh Gupta +2

Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, pr…

cs.LG2026

Memory-Efficient Differentially Private Training with Gradient Random Projection

Alex Mulrooney, Devansh Gupta, James Flemings +4

Differential privacy (DP) protects sensitive data during neural network training, but standard methods like DP-Adam suffer from high memory overhead due to per-sample gradient clip…

cs.CL2026

Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs

Amin Banayeeanzade, Qingchuan Yang, Dhruv Tarsadiya +6

Diversity is essential for language-model applications ranging from creative generation to scientific discovery, yet modern LLMs often collapse into a narrow subset of plausible ou…

cs.LG2026

Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization

Yinbin Han, Meisam Razaviyayn, Renyuan Xu

Diffusion models have become a leading paradigm in generative AI, with score estimation via denoising score matching as a central component. While recent theory provides strong sta…

cs.CL2026

Early Stopping for Large Reasoning Models via Confidence Dynamics

Parsa Hosseini, Sumit Nawathe, Mahdi Salmani +2

Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade p…