The Marginal Value of Momentum for Small Learning Rate SGD
To appear in ICLR 2024.
High-dimensional Learning Dynamics Workshop at ICML 2023.
Fine-Tuning Language Models with Just Forward Passes
Oral presentation at NeurIPS 2023 (OpenReview).
Oral presentation at Efficient Systems for Foundation Models (ES-FoMo) workshop at ICML 2023.
Differentiable Everything Workshop at ICML 2023.
Trainable Transformer in Transformer
In submission.
Robustness of Few-Shot and Zero-Shot Learning in Foundation Models (R0-FoMo) Workshop at NeurIPS 2023.
A Kernel-Based View of Language Model Fine-Tuning
ICML 2023 (OpenReview).
Oral presentation at ICLR 2023 Foundation Models Workshop (ME-FoMo).
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
NeurIPS 2022 (OpenReview).
Oral presentation at ICML 2022 Workshop on Continuous Time Methods.
On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)
NeurIPS 2021 (OpenReview).
A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks
ICLR 2021 (OpenReview).
Oral presentation at NeurIPS 2020 Women in Machine Learning Workshop (Video).
Self-Supervised Learning Workshop at NeurIPS 2020.
Nikunj's Talk at the Vector Institute.
Prediction Propagation for Domain Adaptation in NLP
Towards learning with limited labels: Equivariance, Invariance, and Beyond at ICML 2018.
FastNorm: Improving Numerical Stability of Deep Network Training with Efficient Normalization
Women in Machine Learning Workshop at NeurIPS 2017.
Systematic Analysis of Sex-Linked Molecular Alterations and Therapies in Cancer
Nature Scientific Reports, 2016.
Bioinformatics, 2016.
Journal of Medical Imaging, 2017.