activity
20242026
most citedLimitations on Accurate, Trusted, Human-level Reasoning

1 citations · 1 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

23 papers · 1 filter

cs.LG2026

Discovering Data Structures: Nearest Neighbor Search and Beyond

Omar Salemohamed, Laurent Charlin, Shivam Garg +2

We propose a general framework for end-to-end learning of data structures. Our framework adapts to the underlying data distribution and provides fine-grained control over query and…

cs.LG20261 cited

Limitations on Accurate, Trusted, Human-level Reasoning

Rina Panigrahy, Vatsal Sharan

We identify a fundamental incompatibility between the goals of accuracy, trust, and human-level reasoning in artificial intelligence (AI) systems, for strict mathematical definitio…

cs.LG2026

Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge

Bhavya Vasudeva, Puneesh Deora, Alberto Bietti +2

Transformer-based language models excel at in-context learning (ICL), where they can adapt to new tasks based on contextual examples, without parameter updates. In a specific form…

cs.LG2026

Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data

Qilin Ye, Deqing Fu, Robin Jia +1

Transformers often fail to learn generalizable algorithms, instead relying on brittle heuristics. Using graph connectivity as a testbed, we explain this phenomenon both theoretical…

cs.LG2025

How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data

Bhavya Vasudeva, Puneesh Deora, Yize Zhao +2

The growing adoption of spectrum-aware matrix-valued optimizers such as Muon and Shampoo in deep learning motivates a systematic study of their generalization properties and, in pa…

cs.LG2025

Proper Learnability and the Role of Unlabeled Data

Julian Asilis, Siddartha Devic, Shaddin Dughmi +2

Proper learning refers to the setting in which learners must emit predictors in the underlying hypothesis class , and often leads to learners with simple algorithmic forms (e.g.…