149 citations · 288 across the 9 of their papers we have counts for
9 papers
OMEGA: Optimizing Machine Learning by Evaluating Generated Algorithms
Jeremy Nixon, Annika Singh
In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that starts at idea generation an…
Structure Learning via Mutual Information
Jeremy Nixon
This paper presents a novel approach to machine learning algorithm design based on information theory, specifically mutual information (MI). We propose a framework for learning and…
What are you optimizing for? Aligning Recommender Systems with Human Values
Jonathan Stray, Ivan Vendrov, Jeremy Nixon +2
We describe cases where real recommender systems were modified in the service of various human values such as diversity, fairness, well-being, time well spent, and factual accuracy…
Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
Zachary Nado, Neil Band, Mark Collier +23
High-quality estimates of uncertainty and robustness are crucial for numerous real-world applications, especially for deep learning which underlies many deployed ML systems. The ab…
Semi-Supervised Class Discovery
Jeremy Nixon, Jeremiah Liu, David Berthelot
One promising approach to dealing with datapoints that are outside of the initial training distribution (OOD) is to create new classes that capture similarities in the datapoints p…
Resolving Spurious Correlations in Causal Models of Environments via Interventions
Sergei Volodin, Nevan Wichers, Jeremy Nixon
Causal models bring many benefits to decision-making systems (or agents) by making them interpretable, sample-efficient, and robust to changes in the input distribution. However, s…
Analyzing the Role of Model Uncertainty for Electronic Health Records
Michael W. Dusenberry, Dustin Tran, Edward Choi +5
In medicine, both ethical and monetary costs of incorrect predictions can be significant, and the complexity of the problems often necessitates increasingly complex models. Recent…
Measuring Calibration in Deep Learning
Jeremy Nixon, Mike Dusenberry, Ghassen Jerfel +4
Overconfidence and underconfidence in machine learning classifiers is measured by calibration: the degree to which the probabilities predicted for each class match the accuracy of…
Understanding and correcting pathologies in the training of learned optimizers
Luke Metz, Niru Maheswaranathan, Jeremy Nixon +2
Deep learning has shown that learned functions can dramatically outperform hand-designed functions on perceptual tasks. Analogously, this suggests that learned optimizers may simil…