From the 1 of 2.2k papers with an AI index.
24.4k citations
- Stanford UniversityUS126 papers
- University of California, BerkeleyUS124 papers
- Massachusetts Institute of TechnologyUS123 papers
- Google DeepMind (United Kingdom)GB82 papers
- Cornell UniversityUS76 papers
- Princeton UniversityUS75 papers
- Carnegie Mellon UniversityUS73 papers
- University of TorontoCA73 papers
- California Institute of TechnologyUS63 papers
- Columbia UniversityUS61 papers
- University of California, Santa BarbaraUS58 papers
- University of Illinois Urbana-ChampaignUS56 papers
17 papers · 2 filters
Impossibility Theorems for Feature Attribution
Blair Bilodeau, Natasha Jaques, Pang Wei Koh +1
Despite a sea of interpretability methods that can produce plausible explanations, the field has also empirically seen many failure cases of such methods. In light of these results…
Regression as Classification: Influence of Task Formulation on Neural Network Features
Lawrence Stewart, Francis Bach, Quentin Berthet +1
Neural networks can be trained to solve regression problems by using gradient-based methods to minimize the square loss. However, practitioners often prefer to reformulate regressi…
tf.data service: A Case for Disaggregating ML Input Data Processing
Andrew Audibert, Yang Chen, Dan Graur +3
Machine learning (ML) computations commonly execute on expensive specialized hardware, such as GPUs and TPUs, which provide high FLOPs and performance-per-watt. For cost efficiency…
NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results
Dustin Carrión-Ojeda, Hong Chen, Adrian El Baz +6
We present the design and baseline results for a new challenge in the ChaLearn meta-learning series, accepted at NeurIPS'22, focusing on "cross-domain" meta-learning. Meta-learning…
A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning
Christoph Dann, Mehryar Mohri, Tong Zhang +1
Thompson Sampling is one of the most effective methods for contextual bandits and has been generalized to posterior sampling for certain MDP settings. However, existing posterior s…
SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization
Ningyi Liao, Dingheng Mo, Siqiang Luo +2
Recent advances in data processing have stimulated the demand for learning graphs of very large scales. Graph Neural Networks (GNNs), being an emerging and powerful approach in sol…