activity
20202025
most citedDeep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel

22 citations · 25 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2025

Soup to go: mitigating forgetting during continual learning with model averaging

Anat Kleiman, Gintare Karolina Dziugaite, Jonathan Frankle +2

In continual learning, where task data arrives in a sequence, fine-tuning on later tasks will often lead to performance degradation on earlier tasks. This is especially pronounced…

cs.LG2024

Scaling Laws for Precision

Tanishq Kumar, Zachary Ankner, Benjamin F. Spector +6

Low precision training and inference affect both the quality and cost of language models, but current scaling laws do not account for this. In this work, we devise "precision-aware…

cs.LG20241 cited

Critique-out-Loud Reward Models

Zachary Ankner, Mansheej Paul, Brandon Cui +2

Traditionally, reward models used for reinforcement learning from human feedback (RLHF) are trained to directly predict preference scores without leveraging the generation capabili…

cs.LG2024

Does your data spark joy? Performance gains from domain upsampling at the end of training

Cody Blakeney, Mansheej Paul, Brett W. Larsen +2

Pretraining datasets for large language models (LLMs) have grown to trillions of tokens composed of large amounts of CommonCrawl (CC) web scrape along with smaller, domain-specific…

cs.LG2024

Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models

Zachary Ankner, Cody Blakeney, Kartik Sreenivasan +3

In this work, we investigate whether small language models can determine high-quality subsets of large-scale text datasets that improve the performance of larger language models. W…

cs.LG2024

LoRA Learns Less and Forgets Less

Dan Biderman, Jacob Portes, Jose Javier Gonzalez Ortiz +9

Low-Rank Adaptation (LoRA) is a widely-used parameter-efficient finetuning method for large language models. LoRA saves memory by training only low rank perturbations to selected w…