activity
20212024
most citedAuxiliary Task Update Decomposition: The Good, The Bad and The Neutral

5 citations · 6 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2024

Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes

Steven Kolawole, Lucio Dery, Jean-François Kagy +3

Structured pruning is a promising approach to create smaller, faster large language models. However, existing methods typically rely on computing the gradient via backward passes,…

cs.LG2023

Multitask Learning Can Improve Worst-Group Outcomes

Atharva Kulkarni, Lucio Dery, Amrith Setlur +3

In order to create machine learning systems that serve a variety of users well, it is vital to not only achieve high average performance but also ensure equitable outcomes across d…

cs.LG20231 cited

Cross-Modal Fine-Tuning: Align then Refine

Junhong Shen, Liam Li, Lucio M. Dery +4

Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP. However, similar gains have not been observed in many ot…

cs.LG2022

Multi-step Planning for Automated Hyperparameter Optimization with OptFormer

Lucio M. Dery, Abram L. Friesen, Nando De Freitas +2

As machine learning permeates more industries and models become more expensive and time consuming to train, the need for efficient automated hyperparameter optimization (HPO) has n…

cs.LG20215 cited

Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral

Lucio M. Dery, Yann Dauphin, David Grangier

While deep learning has been very beneficial in data-rich settings, tasks with smaller training set often resort to pre-training or multitask learning to leverage data from other t…