624 citations · 2.4k across the 27 of their papers we have counts for
30 papers
Expected Reward Prediction, with Applications to Model Routing
Kenan Hasanaliyev, Silas Alberti, Jenny Hamer +5
Reward models are a standard tool to score responses from LLMs. Reward models are built to rank responses to a fixed prompt sampled from a single model, for example to choose the b…
Concept Algebra for (Score-Based) Text-Controlled Generative Models
Zihao Wang, Lin Gui, Jeffrey Negrea +1
This paper concerns the structure of learned representations in text-guided generative models, focusing on score-based models. A key property of such models is that they can compos…
Efficient Conditionally Invariant Representation Learning
Roman Pogodin, Namrata Deka, Yazhe Li +3
We introduce the Conditional Independence Regression CovariancE (CIRCE), a measure of conditional independence for multivariate continuous-valued variables. CIRCE applies as a regu…
Causal Estimation for Text Data with (Apparent) Overlap Violations
Lin Gui, Victor Veitch
Consider the problem of estimating the causal effect of some attribute of a text document; for example: what effect does writing a polite vs. rude email have on response time? To e…
The Causal Structure of Domain Invariant Supervised Representation Learning
Zihao Wang, Victor Veitch
Machine learning methods can be unreliable when deployed in domains that differ from the domains on which they were trained. There are a wide range of proposals for mitigating this…
Invariant and Transportable Representations for Anti-Causal Domain Shifts
Yibo Jiang, Victor Veitch
Real-world classification problems must contend with domain shift, the (potential) mismatch between the domain where a model is deployed and the domain(s) where the training data w…
Using Embeddings for Causal Estimation of Peer Influence in Social Networks
Irina Cristali, Victor Veitch
We address the problem of using observational data to estimate peer contagion effects, the influence of treatments applied to individuals in a network on the outcomes of their neig…
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
Amir Feder, Katherine A. Keith, Emaad Manzoor +10
A fundamental goal of scientific research is to learn about causal relationships. However, despite its critical role in the life and social sciences, causality has not had the same…
Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests
Victor Veitch, Alexander D'Amour, Steve Yadlowsky +1
Informally, a 'spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-i…
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Alexander D'Amour, Katherine Heller, Dan Moldovan +37
ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline i…
Invariant Representation Learning for Treatment Effect Estimation
Claudia Shi, Victor Veitch, David Blei
The defining challenge for causal inference from observational data is the presence of `confounders', covariates that affect both treatment assignment and the outcome. To address t…
Causal Effects of Linguistic Properties
Reid Pryzant, Dallas Card, Dan Jurafsky +2
We consider the problem of using observational data to estimate the causal effects of linguistic properties. For example, does writing a complaint politely lead to a faster respons…
Valid Causal Inference with (Some) Invalid Instruments
Jason Hartford, Victor Veitch, Dhanya Sridhar +1
Instrumental variable methods provide a powerful approach to estimating causal effects in the presence of unobserved confounding. But a key challenge when applying them is the reli…
Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding
Victor Veitch, Anisha Zaveri
It is a truth universally acknowledged that an observed association without known mechanism must be in want of a causal estimate. However, causal estimation from observational data…
Adapting Neural Networks for the Estimation of Treatment Effects
Claudia Shi, David M. Blei, Victor Veitch
This paper addresses the use of neural networks for the estimation of treatment effects from observational data. Generally, estimation proceeds in two stages. First, we fit models…
Adapting Text Embeddings for Causal Inference
Victor Veitch, Dhanya Sridhar, David M. Blei
Does adding a theorem to a paper affect its chance of acceptance? Does labeling a post with the author's gender affect the post popularity? This paper develops a method to estimate…
Using Embeddings to Correct for Unobserved Confounding in Networks
Victor Veitch, Yixin Wang, David M. Blei
We consider causal inference in the presence of unobserved confounding. We study the case where a proxy is available for the unobserved confounding in the form of a network connect…
The Holdout Randomization Test for Feature Selection in Black Box Models
Wesley Tansey, Victor Veitch, Haoran Zhang +2
We propose the holdout randomization test (HRT), an approach to feature selection using black box predictive models. The HRT is a specialized version of the conditional randomizati…
Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data
Victor Veitch, Morgane Austern, Wenda Zhou +2
Empirical risk minimization is the main tool for prediction problems, but its extension to relational data remains unsolved. We solve this problem using recent ideas from graph sam…
Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach
Wenda Zhou, Victor Veitch, Morgane Austern +2
Modern neural networks are highly overparameterized, with capacity to substantially overfit to training data. Nevertheless, these networks often generalize well in practice. It has…
Exchangeable modelling of relational data: checking sparsity, train-test splitting, and sparse exchangeable Poisson matrix factorization
Victor Veitch, Ekansh Sharma, Zacharie Naulet +1
A variety of machine learning tasks---e.g., matrix factorization, topic modelling, and feature allocation---can be viewed as learning the parameters of a probability distribution o…
Bootstrap estimators for the tail-index and for the count statistics of graphex processes
Zacharie Naulet, Daniel M. Roy, Ekansh Sharma +1
Graphex processes resolve some pathologies in traditional random graph models, notably, providing models that are both projective and allow sparsity. Most of the literature on grap…
Sampling perspectives on sparse exchangeable graphs
Christian Borgs, Jennifer T. Chayes, Henry Cohn +1
Recent work has introduced sparse exchangeable graphs and the associated graphex framework, as a generalization of dense exchangeable graphs and the associated graphon framework. T…
Sampling and Estimation for (Sparse) Exchangeable Graphs
Victor Veitch, Daniel M. Roy
Sparse exchangeable graphs on , and the associated graphex framework for sparse graphs, generalize exchangeable graphs on , and the associated graphon fra…