Raman, Parameswaran

8 publications

TMLR 2025 νSAM: Memory-Efficient Sharpness-Aware Minimization via Nuclear Norm Constraints Thomas Pethick, Parameswaran Raman, Lenon Minorics, Mingyi Hong, Shoham Sabach, Volkan Cevher

ICML 2024 EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence Chung-Yiu Yau, Hoi To Wai, Parameswaran Raman, Soumajyoti Sarkar, Mingyi Hong

AISTATS 2024 Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate Ruichen Jiang, Parameswaran Raman, Shoham Sabach, Aryan Mokhtari, Mingyi Hong, Volkan Cevher

ICML 2024 MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent Kaan Ozkara, Can Karakus, Parameswaran Raman, Mingyi Hong, Shoham Sabach, Branislav Kveton, Volkan Cevher

ICML 2024 Variance-Reduced Zeroth-Order Methods for Fine-Tuning Language Models Tanmay Gautam, Youngsuk Park, Hao Zhou, Parameswaran Raman, Wooseok Ha

ICLRW 2024 Variance-Reduced Zeroth-Order Methods for Fine-Tuning Language Models Tanmay Gautam, Youngsuk Park, Hao Zhou, Parameswaran Raman, Wooseok Ha

AISTATS 2019 Extreme Stochastic Variational Inference: Distributed Inference for Large Scale Mixture Models Jiong Zhang, Parameswaran Raman, Shihao Ji, Hsiang-Fu Yu, S.V.N. Vishwanathan, Inderjit Dhillon

NeurIPS 2014 Ranking via Robust Binary Classification Hyokun Yun, Parameswaran Raman, S. Vishwanathan