233 citations · 581 across the 28 of their papers we have counts for
29 papers
Reward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models
Alexander Peysakhovich, William Berman
Consider an auto-regressive model that produces outputs x (e.g., answers to questions, molecules) each of which can be summarized by an attribute vector y (e.g., helpfulness vs. ha…
MONET -- Virtual Cell Painting of Brightfield Images and Time Lapses Using Reference Consistent Diffusion
Alexander Peysakhovich, William Berman, Joseph Rufo +2
Cell painting is a popular technique for creating human-interpretable, high-contrast images of cell morphology. There are two major issues with cell paint: (1) it is labor-intensiv…
MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data
William Berman, Alexander Peysakhovich
We train a model to generate images from multimodal prompts of interleaved text and images such as "a <picture of a man> man and his <picture of a dog> dog in an <picture of a cart…
Attention Sorting Combats Recency Bias In Long Context Language Models
Alexander Peysakhovich, Adam Lerer
Current language models often fail to incorporate long contexts efficiently during generation. We show that a major contributor to this issue are attention priors that are likely l…
Diagnosis Uncertain Models For Medical Risk Prediction
Alexander Peysakhovich, Rich Caruana, Yin Aphinyanaphongs
We consider a patient risk models which has access to patient features such as vital signs, lab values, and prior history but does not have access to a patient's diagnosis. For exa…
Observational Causal Inference in Novel Diseases: A Case Study of COVID-19
Alexander Peysakhovich, Yin Aphinyanaphongs
A key issue for all observational causal inference is that it relies on an unverifiable assumption - that observed characteristics are sufficient to proxy for treatment confounding…
Implementing Fairness Constraints in Markets Using Taxes and Subsidies
Alexander Peysakhovich, Christian Kroer, Nicolas Usunier
Fisher markets are those where buyers with budgets compete for scarce items, a natural model for many real world markets including online advertising. A market equilibrium is a set…
Efficient Heterogeneous Treatment Effect Estimation With Multiple Experiments and Multiple Outcomes
Leon Yao, Caroline Lo, Israel Nir +4
Learning heterogeneous treatment effects (HTEs) is an important problem across many fields. Most existing methods consider the setting with a single treatment arm and a single outc…
Pseudo-Euclidean Attract-Repel Embeddings for Undirected Graphs
Alexander Peysakhovich, Anna Klimovskaia Susmel, Leon Bottou
Dot product embeddings take a graph and construct vectors for nodes such that dot products between two vectors give the strength of the edge. Dot products make a strong transitivit…
Online Market Equilibrium with Application to Fair Division
Yuan Gao, Christian Kroer, Alex Peysakhovich
Computing market equilibria is a problem of both theoretical and applied interest. Much research to date focuses on the case of static Fisher markets with full information on buyer…
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
Jack Parker-Holder, Luke Metz, Cinjon Resnick +6
Over the last decade, a single algorithm has changed many facets of our lives - Stochastic Gradient Descent (SGD). In the era of ever decreasing loss functions, SGD and its various…
Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions
Tom Yan, Christian Kroer, Alexander Peysakhovich
Can we predict how well a team of individuals will perform together? How should individuals be rewarded for their contributions to the team performance? Cooperative game theory giv…
"Other-Play" for Zero-Shot Coordination
Hengyuan Hu, Adam Lerer, Alex Peysakhovich +1
We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e.g. humans). Standard Multi-Agent Rei…
Robust Market Equilibria with Uncertain Preferences
Riley Murray, Christian Kroer, Alex Peysakhovich +1
The problem of allocating scarce items to individuals is an important practical question in market design. An increasingly popular set of mechanisms for this task uses the concept…
Scalable Fair Division for 'At Most One' Preferences
Christian Kroer, Alexander Peysakhovich
Allocating multiple scarce items across a set of individuals is an important practical problem. In the case of divisible goods and additive preferences a convex program can be used…
Fair Division Without Disparate Impact
Alexander Peysakhovich, Christian Kroer
We consider the problem of dividing items between individuals in a way that is fair both in the sense of distributional fairness and in the sense of not having disparate impact acr…
PyTorch-BigGraph: A Large-scale Graph Embedding System
Adam Lerer, Ledell Wu, Jiajun Shen +4
Graph embedding methods produce unsupervised node features from graphs that can then be used for a variety of machine learning tasks. Modern graphs, particularly in industrial appl…
Robust Multi-agent Counterfactual Prediction
Alexander Peysakhovich, Christian Kroer, Adam Lerer
We consider the problem of using logged data to make predictions about what would happen if we changed the `rules of the game' in a multi-agent system. This task is difficult becau…
Discovering Context Effects from Raw Choice Data
Arjun Seshadri, Alexander Peysakhovich, Johan Ugander
Many applications in preference learning assume that decisions come from the maximization of a stable utility function. Yet a large experimental literature shows that individual ch…
Computing large market equilibria using abstractions
Christian Kroer, Alexander Peysakhovich, Eric Sodomka +1
Computing market equilibria is an important practical problem for market design, for example in fair division of items. However, computing equilibria requires large amounts of info…
Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2
Alexander Peysakhovich
Inferring a person's goal from their behavior is an important problem in applications of AI (e.g. automated assistants, recommender systems). The workhorse model for this task is t…
Improving pairwise comparison models using Empirical Bayes shrinkage
Stephen Ragain, Alexander Peysakhovich, Johan Ugander
Comparison data arises in many important contexts, e.g. shopping, web clicks, or sports competitions. Typically we are given a dataset of comparisons and wish to train a model to m…
Learning Existing Social Conventions via Observationally Augmented Self-Play
Adam Lerer, Alexander Peysakhovich
In order for artificial agents to coordinate effectively with people, they must act consistently with existing conventions (e.g. how to navigate in traffic, which language to speak…
Consequentialist conditional cooperation in social dilemmas with imperfect information
Alexander Peysakhovich, Adam Lerer
Social dilemmas, where mutual cooperation can lead to high payoffs but participants face incentives to cheat, are ubiquitous in multi-agent interaction. We wish to construct agents…