Publications (29)
Environment Inference for Invariant Learning
Elliot Creager, Jörn-Henrik Jacobsen, Richard Zemel
Learning models that gracefully handle distribution shifts is central to research on domain generalization, robust optimization, and fairness. A promising formulation is domain-inv…
Nonnegative tensor factorization with frequency modulation cues for blind audio source separation
Elliot Creager, Noah D. Stein, Roland Badeau +1
We present Vibrato Nonnegative Tensor Factorization, an algorithm for single-channel unsupervised audio source separation with an application to separating instrumental or vocal so…
On Disentangled Representations Learned From Correlated Data
Frederik Träuble, Elliot Creager, Niki Kilbertus +5
The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often…
Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
Benjamin Eyre, Elliot Creager, David Madras +2
Designing deep neural network classifiers that perform robustly on distributions differing from the available training data is an active area of machine learning research. However,…
Reliable Quasi-Static Post-Fall Floor-Occupancy Detection Using Low-Cost Millimetre-Wave Radar
Huy Trinh, Phuong Thai, Elliot Creager +1
As the population ages rapidly, long-term care (LTC) facilities across North America face growing pressure to monitor residents safely while keeping staff workload manageable. Fall…
Transformers Don't In-Context Learn Least Squares Regression
Joshua Hill, Benjamin Eyre, Elliot Creager
In-context learning (ICL) has emerged as a powerful capability of large pretrained transformers, enabling them to solve new tasks implicit in example input-output pairs without any…
Explaining Image Classifiers by Counterfactual Generation
Chun-Hao Chang, Elliot Creager, Anna Goldenberg +1
When an image classifier makes a prediction, which parts of the image are relevant and why? We can rephrase this question to ask: which parts of the image, if they were not seen by…
Online Algorithmic Recourse by Collective Action
Elliot Creager, Richard Zemel
Research on algorithmic recourse typically considers how an individual can reasonably change an unfavorable automated decision when interacting with a fixed decision-making system.…
Fairness and Robustness in Invariant Learning: A Case Study in Toxicity Classification
Robert Adragna, Elliot Creager, David Madras +1
Robustness is of central importance in machine learning and has given rise to the fields of domain generalization and invariant learning, which are concerned with improving perform…
Robust Machine Learning by Transforming and Augmenting Imperfect Training Data
Elliot Creager
Machine Learning (ML) is an expressive framework for turning data into computer programs. Across many problem domains -- both in industry and policy settings -- the types of comput…
Causal Modeling for Fairness in Dynamical Systems
Elliot Creager, David Madras, Toniann Pitassi +1
In many application areas---lending, education, and online recommenders, for example---fairness and equity concerns emerge when a machine learning system interacts with a dynamical…
MoCoDA: Model-based Counterfactual Data Augmentation
Silviu Pitis, Elliot Creager, Ajay Mandlekar +1
The number of states in a dynamic process is exponential in the number of objects, making reinforcement learning (RL) difficult in complex, multi-object domains. For agents to scal…
Doppler-Domain Respiratory Amplification for Semi-Static Human Occupancy Detection Using Low-Resolution SIMO FMCW Radar
Huy Trinh, Elliot Creager, George Shaker
Radar-based sensing is a promising privacy-preserving alternative to cameras and wearables in settings such as long-term care. Yet detecting quasi-static presence (lying, sitting,…
Conscious Data Contribution via Community-Driven Chain-of-Thought Distillation
Lena Libon, Meghana Bhange, Rushabh Solanki +2
The current era of AI development places a heavy emphasis on training large models on increasingly scaled-up datasets. This paradigm has catalyzed entirely new product categories,…
Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs
Brandon Jaipersaud, Zining Zhu, Frank Rudzicz +1
Tools for analyzing character portrayal in fiction are valuable for writers and literary scholars in developing and interpreting compelling stories. Existing tools, such as visuali…
Counterfactual Data Augmentation using Locally Factored Dynamics
Silviu Pitis, Elliot Creager, Animesh Garg
Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses. Though the subprocesses are not in…
Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
David Madras, Elliot Creager, Toniann Pitassi +1
How do we learn from biased data? Historical datasets often reflect historical prejudices; sensitive or protected attributes may affect the observed treatments and outcomes. Classi…
SURFSUP: Learning Fluid Simulation for Novel Surfaces
Arjun Mani, Ishaan Preetam Chandratreya, Elliot Creager +2
Modeling the mechanics of fluid in complex scenes is vital to applications in design, graphics, and robotics. Learning-based methods provide fast and differentiable fluid simulator…
DriftXpress: Faster Drifting Models via Projected RKHS Fields
Ali Falahati, Elliot Creager, Gautam Kamath +1
Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise is to replace the iterative…
Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach
Martin Mladenov, Elliot Creager, Omer Ben-Porat +3
Most recommender systems (RS) research assumes that a user's utility can be maximized independently of the utility of the other agents (e.g., other users, content providers). In re…
Test-Time Collective Action: Proxy-Based Perturbations for Correcting Algorithmic Harms
Meghana Bhange, Ulrich Aïvodji, Ulrich Aïvodji +1
When machine learning systems under-perform for particular subgroups, affected users typically have no way to correct these disparities without relying on platform-level fixes. Exi…
A Physics-Informed Digital Twin Framework for Calibrated Sim-to-Real FMCW Radar Occupancy Estimation
Huy Trinh, Sebastian Ratto, Elliot Creager +1
Learning robust radar perception models directly from real measurements is costly due to the need for controlled experiments, repeated calibration, and extensive annotation. This p…
Promoting User Data Autonomy During the Dissolution of a Monopolistic Firm
Rushabh Solanki, Elliot Creager
The deployment of AI in consumer products is currently focused on the use of so-called foundation models, large neural networks pre-trained on massive corpora of digital records. T…
Learning Adversarially Fair and Transferable Representations
David Madras, Elliot Creager, Toniann Pitassi +1
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are use…
Active Slice Discovery in Large Language Models
Minhui Zhang, Prahar Ijner, Yoav Wald +1
Large Language Models (LLMs) often exhibit systematic errors on specific subsets of data, known as error slices. For instance, a slice can correspond to a certain demographic, wher…
Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework
Cléa Chataigner, Rebecca Ma, Prakhar Ganesh +4
Large language models (LLMs) are highly sensitive to subtle changes in prompt phrasing, posing challenges for reliable auditing. Prior methods often apply unconstrained prompt para…
Flexibly Fair Representation Learning by Disentanglement
Elliot Creager, David Madras, Jörn-Henrik Jacobsen +4
We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled…
Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacy
Rushabh Solanki, Meghana Bhange, Ulrich Aïvodji +1
The integration of AI into daily life has generated considerable attention and excitement, while also raising concerns about automating algorithmic harms and re-entrenching existin…
Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making
Parand A. Alamdari, Toryn Q. Klassen, Elliot Creager +1
Fair decision making has largely been studied with respect to a single decision. Here we investigate the notion of fairness in the context of sequential decision making where multi…