AW
Andrew Gordon Wilson
cs.LGstat.MLcs.AIcs.CVstat.MEcs.CLcond-mat.str-elcs.DCmath.DSmath.OC
On Valency
published · living versionsW_u7fa5rax·v1 · currentpublished
MLSys: The New Frontier of Machine Learning Systems
with Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen +64
1 version
Preprints & journals
120 papers in the corpus · 2011–2026How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents2609.19107v2 · Zixi Chen, Akshay Vegesna, Samip Dahal et al.2026 · 0 citationsarXiv
DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking2605.26087v2 · Matt L. Wiemann, Lindsay M. Smith, Peter Melchior et al.2026 · 0 citationsarXiv
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data2607.11883v1 · Shikai Qiu, Marc Finzi, Yujia Zheng et al.2026 · 0 citationsarXiv
Position: agentic AI orchestration should be Bayes-consistent2605.00742v2 · Theodore Papamarkou, Pierre Alquier, Matthias Bauer et al.2026 · 0 citationsarXiv
Diverse Dictionary Learning2604.17568v1 · Yujia Zheng, Zijian Li, Shunxing Fan et al.2026 · 0 citationsarXiv
From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence2601.03220v2 · Marc Finzi, Shikai Qiu, Yiding Jiang et al.2026 · 2 citationsarXiv
A Diffusion Model to Shrink Proteins While Maintaining Their Function2511.07390v2 · Ethan Baron, Alan N. Amin, Ruben Weitzman et al.2025 · 2 citationsarXiv
Materials Expert-Artificial Intelligence for Materials Discovery2312.02796v1 · Yanjun Liu, Milena Jovanovic, Krishnanand Mallayya et al.2023 · 12 citationsCommunications Materials 6, 212 (2025)
In-Context Clustering with Large Language Models2510.08466v1 · Ying Wang, Mengye Ren, Andrew Gordon Wilson2025 · 0 citationsarXiv
Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion2506.08316v2 · Alan N. Amin, Nate Gruver, Andrew Gordon Wilson2025 · 0 citationsarXiv
Response to Promises and Pitfalls of Deep Kernel Learning2509.21228v1 · Andrew Gordon Wilson, Zhiting Hu, Ruslan Salakhutdinov et al.2025 · 0 citationsarXiv
Fine-Tuned Language Models Generate Stable Inorganic Materials as Text2402.04379v2 · Nate Gruver, Anuroop Sriram, Andrea Madotto et al.2024 · 35 citationsarXiv
Deep Learning is Not So Mysterious or Different2503.02113v2 · Andrew Gordon Wilson2025 · 2 citationsarXiv
Out-of-Distribution Detection Methods Answer the Wrong Questions2507.01831v1 · Yucen Lily Li, Daohan Lu, Polina Kirichenko et al.2025 · 0 citationsarXiv
Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra2506.19598v2 · Alan N. Amin, Andres Potapczynski, Andrew Gordon Wilson2025 · 0 citationsarXiv
Transformers Boost the Performance of Decision Trees on Tabular Data across Sample Sizes2502.02672v2 · Mayuka Jayawardhana, Renbo, Samuel Dooley et al.2025 · 0 citationsarXiv
Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences2412.07763v1 · Alan Nawzad Amin, Nate Gruver, Yilun Kuang et al.2024 · 3 citationsarXiv
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices2410.02117v2 · Andres Potapczynski, Shikai Qiu, Marc Finzi et al.2024 · 1 citationarXiv
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI2402.00809v5 · Theodore Papamarkou, Maria Skoularidou, Konstantina Palla et al.2024 · 8 citationsarXiv
Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models2407.18158v1 · Sanae Lotfi, Yilun Kuang, Brandon Amos et al.2024 · 2 citationsarXiv
Non-Vacuous Generalization Bounds for Large Language Models2312.17173v3 · Sanae Lotfi, Marc Finzi, Yilun Kuang et al.2023 · 0 citationsarXiv
The Lie Derivative for Measuring Learned Equivariance2210.02984v2 · Nate Gruver, Marc Finzi, Micah Goldblum et al.2022 · 6 citationsarXiv
Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency2406.09177v2 · Alan Nawzad Amin, Andrew Gordon Wilson2024 · 0 citationsarXiv
Just How Flexible are Neural Networks in Practice?2406.11463v1 · Ravid Shwartz-Ziv, Micah Goldblum, Arpit Bansal et al.2024 · 1 citationarXiv
Transferring Knowledge from Large Foundation Models to Small Downstream Models2406.07337v1 · Shikai Qiu, Boran Han, Danielle C. Maddix et al.2024 · 1 citationarXiv
The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning2304.05366v3 · Micah Goldblum, Marc Finzi, Keefer Rowan et al.2023 · 15 citationsarXiv
Compute Better Spent: Replacing Dense Layers with Structured Matrices2406.06248v1 · Shikai Qiu, Andres Potapczynski, Marc Finzi et al.2024 · 0 citationsarXiv
Controllable Prompt Tuning For Balancing Group Distributional Robustness2403.02695v2 · Hoang Phan, Andrew Gordon Wilson, Qi Lei2024 · 0 citationsarXiv
A Study of Bayesian Neural Network Surrogates for Bayesian Optimization2305.20028v2 · Yucen Lily Li, Tim G. J. Rudner, Andrew Gordon Wilson2023 · 5 citationsarXiv
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion2403.16365v1 · Hossein Souri, Arpit Bansal, Hamid Kazemi et al.2024 · 0 citationsarXiv
Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors2403.09869v1 · Tim G. J. Rudner, Ya Shi Zhang, Andrew Gordon Wilson et al.2024 · 1 citationarXiv
Function-Space Regularization in Neural Networks: A Probabilistic Perspective2312.17162v1 · Tim G. J. Rudner, Sanyam Kapoor, Shikai Qiu et al.2023 · 1 citationarXiv
Perspectives on the State and Future of Deep Learning - 20232312.09323v3 · Micah Goldblum, Anima Anandkumar, Richard Baraniuk et al.2023 · 4 citationsarXiv
Bayesian Optimization with Conformal Prediction Sets2210.12496v4 · Samuel Stanton, Wesley Maddox, Andrew Gordon Wilson2022 · 1 citationProceedings of Machine Learning Research, Volume 206, 959-986, PMLR, 2023
Automated Few-shot Classification with Instruction-Finetuned Language Models2305.12576v2 · Rami Aly, Xingjian Shi, Kaixiang Lin et al.2023 · 2 citationsarXiv
A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks2304.14994v2 · Marc Finzi, Andres Potapczynski, Matthew Choptuik et al.2023 · 1 citationarXiv
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations2204.02937v2 · Polina Kirichenko, Pavel Izmailov, Andrew Gordon Wilson2022 · 32 citationsarXiv
A Cookbook of Self-Supervised Learning2304.12210v2 · Randall Balestriero, Mark Ibrahim, Vlad Sobal et al.2023 · 165 citationsarXiv
Simple and Fast Group Robustness by Automatic Feature Reweighting2306.11074v1 · Shikai Qiu, Andres Potapczynski, Pavel Izmailov et al.2023 · 4 citations40th International Conference on Machine Learning 2023
User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems2306.07526v1 · Marc Finzi, Anudhyan Boral, Andrew Gordon Wilson et al.2023 · 3 citationsarXiv
Bayesian Model Selection, the Marginal Likelihood, and Generalization2202.11678v3 · Sanae Lotfi, Pavel Izmailov, Gregory Benton et al.2022 · 17 citationsarXiv
Learning Multimodal Data Augmentation in Feature Space2212.14453v2 · Zichang Liu, Zhiqiang Tang, Xingjian Shi et al.2022 · 9 citationsarXiv
How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization2210.06441v2 · Jonas Geiping, Micah Goldblum, Gowthami Somepalli et al.2022 · 12 citationsarXiv
Fortuna: A Library for Uncertainty Quantification in Deep Learning2302.04019v1 · Gianluca Detommaso, Alberto Gasparin, Michele Donini et al.2023 · 2 citationsarXiv
What do Vision Transformers Learn? A Visual Exploration2212.06727v1 · Amin Ghiasi, Hamid Kazemi, Eitan Borgnia et al.2022 · 20 citationsarXiv
K-SAM: Sharpness-Aware Minimization at the Speed of SGD2210.12864v1 · Renkun Ni, Ping-yeh Chiang, Jonas Geiping et al.2022 · 2 citationsarXiv
Unsupervised learning of two-component nematicity from STM data on magic angle bilayer graphene2203.04449v2 · William Taranto, Samuel Lederer, Youngjoon Choi et al.2022 · 2 citationsarXiv
Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes2207.06544v1 · Gregory Benton, Wesley J. Maddox, Andrew Gordon Wilson2022 · 1 citationarXiv
Low-Precision Arithmetic for Fast Gaussian Processes2207.06856v1 · Wesley J. Maddox, Andres Potapczynski, Andrew Gordon Wilson2022 · 0 citationsarXiv
Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders2203.12742v2 · Samuel Stanton, Wesley Maddox, Nate Gruver et al.2022 · 22 citationsarXiv
Career total: 155 works. 120 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.