page under active development
QuantEase: Optimization-based Quantization for Language Models–An Efficient and Intuitive Algorithm; K Behdin, A Acharya, A Gupta, S Keerthi, R Mazumder; arXiv preprint arXiv:2309.01885
mSAM: Micro-Batch-Averaged Sharpness-Aware Minimization; K Behdin, Q Song, A Gupta, A Acharya, D Durfee, B Ocejo, S Keerthi; arXiv preprint arXiv:2302.09693
A Precise Characterization of SGD Stability Using Loss Surface Geometry; G Dexter, B Ocejo, S Keerthi, A Gupta, A Acharya, R Khanna; ICLR 2024
Optimizing for Member Value in an Edge Building Marketplace; A Acharya, S Gao, A Saha, B Ocejo, K Basu, K Selvaraj, R Mazumder; CIKM 2023
Improved deep neural network generalization using m-sharpness-aware minimization; K Behdin, Q Song, A Gupta, D Durfee, A Acharya, S Keerthi, R Mazumder; NeurIPS 2023 OPT Workshop
Variational Graph Auto-Encoders for Heterogeneous Information Network; A Dalvi, A Acharya, J Gao, VG Honavar, NeurIPS 2022 Workshop GLFrontiers
A dual Markov chain topic model for dynamic environments; A Acharya, J Ghosh, M Zhou KDD 2018