274 citations · 433 across the 19 of their papers we have counts for
19 papers
TailSFT: Filtered Fine-Tuning Improves Post-Training Performance
Sadhika Malladi, Samy Jelassi, Dylan Foster +2
Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most effective when used to fine-tu…
The Coverage Principle: How Pre-Training Enables Post-Training
Fan Chen, Audrey Huang, Noah Golowich +5
Language models demonstrate remarkable abilities when pre-trained on large text corpora and fine-tuned for specific tasks, but how and why pre-training shapes the success of the fi…
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Jens Tuyls, Dylan J. Foster, Akshay Krishnamurthy +1
Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply s…
On the Query Complexity of Verifier-Assisted Language Generation
Edoardo Botta, Yuchen Li, Aashay Mehta +3
Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade…
Self-Improvement in Language Models: The Sharpening Mechanism
Audrey Huang, Adam Block, Dylan J. Foster +5
Recent work in language modeling has raised the possibility of self-improvement, where a language models evaluates and refines its own generations to achieve higher performance wit…
Exposing Attention Glitches with Flip-Flop Language Modeling
Bingbin Liu, Jordan T. Ash, Surbhi Goel +2
Why do large language models sometimes output factual inaccuracies and exhibit erroneous reasoning? The brittleness of these models, particularly when executing long chains of reas…
Streaming Active Learning with Deep Neural Networks
Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy +2
Active learning is perhaps most naturally posed as an online learning problem. However, prior active learning approaches with deep neural networks assume offline access to the enti…
Neural Active Learning on Heteroskedastic Distributions
Savya Khosla, Chew Kin Whye, Jordan T. Ash +3
Models that can actively seek out the best quality training data hold the promise of more accurate, adaptable, and efficient machine learning. Active learning techniques often tend…
Eigen Memory Trees
Mark Rucker, Jordan T. Ash, John Langford +2
This work introduces the Eigen Memory Tree (EMT), a novel online memory model for sequential learning scenarios. EMTs store data at the leaves of a binary tree and route new sample…
Transformers Learn Shortcuts to Automata
Bingbin Liu, Jordan T. Ash, Surbhi Goel +2
Algorithmic reasoning requires capabilities which are most naturally understood through recurrent models of computation, like the Turing machine. However, Transformer models, while…
Understanding Contrastive Learning Requires Incorporating Inductive Biases
Nikunj Saunshi, Jordan Ash, Surbhi Goel +5
Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmenta…
Anti-Concentrated Confidence Bonuses for Scalable Exploration
Jordan T. Ash, Cyril Zhang, Surbhi Goel +2
Intrinsic rewards play a central role in handling the exploration-exploitation trade-off when designing sequential decision-making algorithms, in both foundational theory and state…
Investigating the Role of Negatives in Contrastive Representation Learning
Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy +1
Noise contrastive learning is a popular technique for unsupervised representation learning. In this approach, a representation is obtained via reduction to supervised learning, whe…
Gone Fishing: Neural Active Learning with Fisher Embeddings
Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy +1
There is an increasing need for effective active learning algorithms that are compatible with deep neural networks. This paper motivates and revisits a classic, Fisher-based active…
Learning Composable Energy Surrogates for PDE Order Reduction
Alex Beatson, Jordan T. Ash, Geoffrey Roeder +2
Meta-materials are an important emerging class of engineered materials in which complex macroscopic behaviour--whether electromagnetic, thermal, or mechanical--arises from modular…
On Warm-Starting Neural Network Training
Jordan T. Ash, Ryan P. Adams
In many real-world deployments of machine learning systems, data arrive piecemeal. These learning scenarios may be passive, where data arrive incrementally due to structural proper…
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy +2
We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of…
Learning Deep ResNet Blocks Sequentially using Boosting Theory
Furong Huang, Jordan Ash, John Langford +1
Deep neural networks are known to be difficult to train due to the instability of back-propagation. A deep \emph{residual network} (ResNet) with identity loops remedies this by sta…
Unsupervised Domain Adaptation Using Approximate Label Matching
Jordan T. Ash, Robert E. Schapire, Barbara E. Engelhardt
Domain adaptation addresses the problem created when training data is generated by a so-called source distribution, but test data is generated by a significantly different target d…