44 citations · 91 across the 7 of their papers we have counts for
7 papers
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Kaiyu Yang, Aidan M. Swope, Alex Gu +6
Large language models (LLMs) have shown promise in proving formal theorems using proof assistants such as Lean. However, existing methods are difficult to reproduce or build on, du…
Certified Interpretability Robustness for Class Activation Mapping
Alex Gu, Tsui-Wei Weng, Pin-Yu Chen +2
Interpreting machine learning models is challenging but crucial for ensuring the safety of deep networks in autonomous driving systems. Due to the prevalence of deep learning based…
ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications
Alex Gu, Tamara Mitrovska, Daniela Velez +2
We introduce ObSynth, an interactive system leveraging the domain knowledge embedded in large language models (LLMs) to help users design object models from high level natural lang…
Min-Max Bilevel Multi-objective Optimization with Applications in Machine Learning
Alex Gu, Songtao Lu, Parikshit Ram +1
We consider a generic min-max multi-objective bilevel optimization problem with applications in robust machine learning such as representation learning and hyperparameter optimizat…
The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
Satyapriya Krishna, Tessa Han, Alex Gu +3
As various post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to develop a deeper understanding of…
Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates
Alp Yurtsever, Alex Gu, Suvrit Sra
Three Operator Splitting (TOS) (Davis & Yin, 2017) can minimize the sum of multiple convex functions effectively when an efficient gradient oracle or proximal operator is available…
Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning
Joel Joseph, Alex Gu
The Continual Learning (CL) problem involves performing well on a sequence of tasks under limited compute. Current algorithms in the domain are either slow, offline or sensitive to…