Jordan T. Ash

ash.jordan -at-

google scholar twitter msr

I'm a senior researcher at Microsoft Research in New York City, where I mostly think about problems related to deep learning and sequential decision making. I earned my PhD from the computer science department at Princeton University and was advised by Ryan P. Adams.

Selected Papers

A study of plasticity loss in on-policy deep reinforcement learning
Arthur Juliani and Jordan T. Ash. 2024.

An experimental design framework for label-efficient supervised finetuning of large language models
Gantavya Bhatt, Yifang Chen, Arnav M. Das, Jifan Zhang, Sang T. Truong, Stephen Mussmann, Yinglun Zhu, Jeffrey Bilmes, Simon S. Du, Kevin Jamieson, Jordan T. Ash and Robert D. Nowak. ACL 2024.

The truth is in there: Improving reasoning in language models with layer-selective rank reduction
Pratyusha Sharma, Jordan T. Ash and Dipendra Misra. ICLR 2024.
paper / code

Exposing attention glitches with flip-flop language modeling
Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy and Cyril Zhang. NeurIPS 2023 (short talk).

Streaming active learning with deep neural networks
Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy, John Langford and Jordan T. Ash. ICML 2023.
paper / code

Transformers learn shortcuts to automata
Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy and Cyril Zhang. ICLR 2023 (talk).

Eigen memory trees
Mark Rucker, Jordan T. Ash, John Langford, Paul Mineiro and Ida Momennejad. 2022.

Understanding contrastive learning requires incorporating inductive biases
Nikunj Saunshi, Jordan T. Ash, Surbhi Goel, Dipendra Misra, Cyril Zhang, Sanjeev Arora, Sham Kakade and Akshay Krishnamurthy. ICML 2022 (short talk).

Anti-concentrated confidence bonuses for scalable exploration
Jordan T. Ash, Cyril Zhang, Surbhi Goel, Akshay Krishnamurthy and Sham Kakade. ICLR 2022.
paper / code

Investigating the role of negatives in contrastive representation learning
Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy and Dipendra Misra. AISTATS 2022.

Gone fishing: neural active learning with Fisher embeddings
Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy and Sham Kakade. NeurIPS 2021.
paper / code

Joint analysis of gene expression levels and histological images identifies genes associated with tissue morphology
Jordan T. Ash, Gregory Darnell, Daniel Munro and Barbara E. Engelhardt. Nature Communications 2021.
paper / code

Learning composable energy surrogates for PDE order reduction
Alex Beatson, Jordan T. Ash, Geoffrey Roeder, Tianju Xie and Ryan P. Adams. NeurIPS 2020 (talk).
paper / code

On warm-starting neural network training
Jordan T. Ash and Ryan P. Adams. NeurIPS 2020.
paper / code

A data-driven computational scheme for the nonlinear mechanical properties of cellular mechanical metamaterials under large deformation
Tianju Xue, Alex Beatson, Maurizio Chiaramonte, Geoffrey Roeder, Jordan T. Ash, Yigit Menguc, Sigrid Adriaenssens, Ryan P. Adams and Sheng Mao. Soft Matter 2020.

Deep batch active learning by diverse, uncertain gradient lower bounds
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford and Alekh Agarwal. ICLR 2020 (talk).
paper / code

End-to-end training of deep probabilistic CCA for joint modeling of paired biomedical observations
Gregory Gundersen, Bianca Dumitrascu, Jordan T. Ash and Barbara E. Engelhardt. UAI 2019.
paper / code

Learning deep resnet blocks sequentially using boosting theory
Furong Huang, Jordan T. Ash, John Langford and Rob Schapire. ICML 2018.
paper / code

Unsupervised domain adaptation using approximate label matching
Jordan T. Ash, Rob Schapire and Barbara E. Engelhardt. ICML workshop on implicit generative models 2017.

Automated particle picking for low-contrast macromolecules in cryo-electron microscopy
Robert Langlois, Jesper Pallesen, Jordan T. Ash, Danny Nam Ho, John L. Rubinstein and Joachim Frank. Journal of structural biology 2014.
paper / code

Fully automated particle selection and verification in single-particle cryo-EM
Robert Langlois, Jordan T. Ash, Jesper Pallesen and Joachim Frank. Computational Methods for Three-Dimensional Microscopy Reconstruction, Springer 2014.
book chapter