Understanding Optimal Feature Transfer via a Fine-Grained Bias-Variance Analysis Y Li, S Sen, B Adlam arXiv preprint arXiv:2404.12481, 2024 | | 2024 |
Beyond human data: Scaling self-training for problem-solving with language models A Singh, JD Co-Reyes, R Agarwal, A Anand, P Patil, PJ Liu, J Harrison, ... arXiv preprint arXiv:2312.06585, 2023 | 36 | 2023 |
Frontier Language Models are not Robust to Adversarial Arithmetic, or" What do I need to say so you agree 2+ 2= 5? CD Freeman, L Culp, A Parisi, ML Bileschi, GF Elsayed, A Rizkowsky, ... arXiv preprint arXiv:2311.07587, 2023 | | 2023 |
Small-scale proxies for large-scale Transformer training instabilities M Wortsman, PJ Liu, L Xiao, K Everett, A Alemi, B Adlam, JD Co-Reyes, ... The Twelfth International Conference on Learning Representations, 2023 | 24 | 2023 |
Kernel regression with infinite-width neural networks on millions of examples B Adlam, J Lee, S Padhy, Z Nado, J Snoek arXiv preprint arXiv:2303.05420, 2023 | 8 | 2023 |
Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties C Paquette, E Paquette, B Adlam, J Pennington arXiv preprint arXiv:2205.07069, 2022 | 23 | 2022 |
Understanding the bias-variance tradeoff of Bregman divergences B Adlam, N Gupta, Z Mariet, J Smith arXiv preprint arXiv:2202.04167, 2022 | 3 | 2022 |
Ensembles of Classifiers: a Bias-Variance Perspective N Gupta, J Smith, B Adlam, ZE Mariet Transactions of Machine Learning Research, 2022 | 10* | 2022 |
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions C Paquette, E Paquette, B Adlam, J Pennington Advances in Neural Information Processing Systems 36, 2022 | 13 | 2022 |
Underspecification presents challenges for credibility in modern machine learning A D'Amour, K Heller, D Moldovan, B Adlam, B Alipanahi, A Beutel, ... Journal of Machine Learning Research 23 (226), 1-61, 2022 | 725 | 2022 |
A Random Matrix Perspective on Mixtures of Nonlinearities in High Dimensions B Adlam, J Levinson, J Pennington International Conference on Artificial Intelligence and Statistics, 2022 | 37* | 2022 |
Overparameterization improves robustness to covariate shift in high dimensions N Tripuraneni, B Adlam, J Pennington Advances in Neural Information Processing Systems 34, 13883-13897, 2021 | 48 | 2021 |
Covariate shift in high-dimensional random feature regression N Tripuraneni, B Adlam, J Pennington arXiv preprint arXiv:2111.08234, 2021 | 27 | 2021 |
Dynamics of COVID-19 under social distancing measures are driven by transmission network structure A Nande, B Adlam, J Sheen, MZ Levy, AL Hill PLoS computational biology 17 (2), e1008684, 2021 | 107 | 2021 |
The effect of eviction moratoria on the transmission of SARS-CoV-2 ALH Anjalika Nande, Justin Sheen, Emma L Walters, Brennan Klein, Matteo ... Nature Communications 12 (2274), 2021 | 95 | 2021 |
Exploring the Uncertainty Properties of Neural Networks’ Implicit Priors in the Infinite-Width Limit B Adlam, J Lee, L Xiao, J Pennington, Snoek, Jasper The Ninth International Conference on Learning Representations, 2021 | 19 | 2021 |
Crowding and the shape of COVID-19 epidemics B Rader, SV Scarpino, A Nande, AL Hill, B Adlam, RC Reiner, DM Pigott, ... Nature Medicine, 1-6, 2020 | 293* | 2020 |
Cold Posteriors and Aleatoric Uncertainty B Adlam, J Snoek, SL Smith ICML Workshop on Uncertainty & Robustness in Deep Learning, 2020 | 20 | 2020 |
Finite Versus Infinite Neural Networks: an Empirical Study J Lee, S Schoenholz, J Pennington, B Adlam, L Xiao, R Novak, ... Advances in Neural Information Processing Systems, 2020 | 204 | 2020 |
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks W Hu, L Xiao, B Adlam, J Pennington Advances in Neural Information Processing Systems, 2020 | 73 | 2020 |