6 papers
ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
Lejs Deen Behric, Liang Zhang, Bingcong Li +1
Zeroth-order or derivative-free optimization (MeZO) is an attractive strategy for finetuning large language models (LLMs) because it eliminates the memory overhead of backpropagati…
Zeroth-Order Optimization Finds Flat Minima
Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil +3
Zeroth-order methods are extensively used in machine learning applications where gradients are infeasible or expensive to compute, such as black-box attacks, reinforcement learning…
RewardRank: Optimizing True Learning-to-Rank Utility
Gaurav Bhatt, Kiran Koshy Thekumparampil, Tanmay Gangwani +2
Traditional ranking systems optimize offline proxy objectives that rely on oversimplified assumptions about user behavior, often neglecting factors such as position bias and item d…
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
Charlie Hou, Kiran Koshy Thekumparampil, Michael Shavlovsky +3
On tabular data, a significant body of literature has shown that current deep learning (DL) models perform at best similarly to Gradient Boosted Decision Trees (GBDTs), while signi…
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
Rohan Deb, Kiran Thekumparampil, Kousha Kalantari +3
Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting…
Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe
Kiran Koshy Thekumparampil, Gaurush Hiranandani, Kousha Kalantari +2
We study learning of human preferences from a limited comparison feedback. This task is ubiquitous in machine learning. Its applications such as reinforcement learning from human f…