10.9k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Harvard UniversityUS735 papers
- Massachusetts Institute of TechnologyUS455 papers
- University of OxfordGB379 papers
- University of ChicagoUS368 papers
- University of MichiganUS356 papers
- Lawrence Berkeley National LaboratoryUS354 papers
- The Ohio State UniversityUS350 papers
- Yale UniversityUS348 papers
- University of PittsburghUS317 papers
- Argonne National LaboratoryUS316 papers
- University College LondonGB312 papers
- University of PisaIT310 papers
59 papers · 2 filters
Noether Networks: Meta-Learning Useful Conserved Quantities
Ferran Alet, Dylan Doblar, Allan Zhou +3
Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often explo…
Recommending with Recommendations
Naveen Durvasula, Franklyn Wang, Scott Duke Kominers
Recommendation systems are a key modern application of machine learning, but they have the downside that they often draw upon sensitive user information in making their predictions…
Machine Learning for Real-Time, Automatic, and Early Diagnosis of Parkinson's Disease by Extracting Signs of Micrographia from Handwriting Images
Riya Tyagi, Tanish Tyagi, Ming Wang +1
Parkinson's disease (PD) is debilitating, progressive, and clinically marked by motor symptoms. As the second most common neurodegenerative disease in the world, it affects over 10…
Depth induces scale-averaging in overparameterized linear Bayesian neural networks
Jacob A. Zavatone-Veth, Cengiz Pehlevan
Inference in deep Bayesian neural networks is only fully understood in the infinite-width limit, where the posterior flexibility afforded by increased depth washes out and the post…
The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage
Daniel Galvez, Greg Diamos, Juan Ciro +7
The People's Speech is a free-to-download 30,000-hour and growing supervised conversational English speech recognition dataset licensed for academic and commercial usage under CC-B…
On the Existence of Universal Lottery Tickets
Rebekka Burkholz, Nilanjana Laha, Rajarshi Mukherjee +1
The lottery ticket hypothesis conjectures the existence of sparse subnetworks of large randomly initialized deep neural networks that can be successfully trained in isolation. Rece…
Collaboration Promotes Group Resilience in Multi-Agent RL
Ilai Shraga, Guy Azran, Matthias Gerstgrasser +3
To effectively operate in various dynamic scenarios, RL agents must be resilient to unexpected changes in their environment. Previous work on this form of resilience has focused on…
Attention Approximates Sparse Distributed Memory
Trenton Bricken, Cengiz Pehlevan
While Attention has come to be an important mechanism in deep learning, there remains limited intuition for why it works so well. Here, we show that Transformer Attention can be cl…
TinyFedTL: Federated Transfer Learning on Tiny Devices
Kavya Kopparapu, Eric Lin
TinyML has rose to popularity in an era where data is everywhere. However, the data that is in most demand is subject to strict privacy and security guarantees. In addition, the de…
Chaos as an interpretable benchmark for forecasting and data-driven modelling
William Gilpin
The striking fractal geometry of strange attractors underscores the generative nature of chaos: like probability distributions, chaotic systems can be repeatedly measured to produc…
MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation
Alexandros Karargyris, Renato Umeton, Micah J. Sheller +39
Medical AI has tremendous potential to advance healthcare by supporting the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving prov…
A Spectral Approach to Off-Policy Evaluation for POMDPs
Yash Nair, Nan Jiang
We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes, where the evaluation policy depends only on observable variables but the behavior policy…
Comparison and Unification of Three Regularization Methods in Batch Reinforcement Learning
Sarah Rathnam, Susan A. Murphy, Finale Doshi-Velez
In batch reinforcement learning, there can be poorly explored state-action pairs resulting in poorly learned, inaccurate models and poorly performing associated policies. Various r…
State Relevance for Off-Policy Evaluation
Simon P. Shen, Yecheng Jason Ma, Omer Gottesman +1
Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions. However, the varianc…
Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing
Sindhu C. M. Gowda, Shalmali Joshi, Haoran Zhang +1
Machine learning models achieve state-of-the-art performance on many supervised learning tasks. However, prior evidence suggests that these models may learn to rely on shortcut bia…
Unsupervised Reservoir Computing for Solving Ordinary Differential Equations
Marios Mattheakis, Hayden Joy, Pavlos Protopapas
There is a wave of interest in using unsupervised neural networks for solving differential equations. The existing methods are based on feed-forward networks, {while} recurrent neu…
Zero-Round Active Learning
Si Chen, Tianhao Wang, Ruoxi Jia
Active learning (AL) aims at reducing labeling effort by identifying the most valuable unlabeled data points from a large pool. Traditional AL frameworks have two limitations: Firs…
The staircase property: How hierarchical structure can guide deep learning
Emmanuel Abbe, Enric Boix-Adsera, Matthew Brennan +2
This paper identifies a structural property of data distributions that enables deep neural networks to learn hierarchically. We define the "staircase" property for functions over t…
Online structural kernel selection for mobile health
Eura Shin, Pedja Klasnja, Susan Murphy +1
Motivated by the need for efficient and personalized learning in mobile health, we investigate the problem of online kernel selection for Gaussian Process regression in the multi-t…
Early-Phase Performance-Driven Design using Generative Models
Spyridon Ampanavos, Ali Malkawi
Current performance-driven building design methods are not widely adopted outside the research field for several reasons that make them difficult to integrate into a typical design…
Deep Contextual Learners for Protein Networks
Michelle M. Li, Marinka Zitnik
Spatial context is central to understanding health and disease. Yet reference protein interaction networks lack such contextualization, thereby limiting the study of where protein…
Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification
Alkis Gotovos, Rebekka Burkholz, John Quackenbush +1
Modeling the time evolution of discrete sets of items (e.g., genetic mutations) is a fundamental problem in many biomedical applications. We approach this problem through the lens…
Memory-Sample Lower Bounds for Learning Parity with Noise
Sumegha Garg, Pravesh K. Kothari, Pengda Liu +1
In this work, we show, for the well-studied problem of learning parity under noise, where a learner tries to learn from a stream of random linear…
Q-Learning Lagrange Policies for Multi-Action Restless Bandits
Jackson A. Killian, Arpita Biswas, Sanket Shah +1
Multi-action restless multi-armed bandits (RMABs) are a powerful framework for constrained resource allocation in which independent processes are managed. However, previous wor…