10 papers
Parameter-Free and Group Conditional Online Conformal Prediction
Beepul Bharti, Ambar Pal, Jacopo Teneggi +1
Uncertainty quantification (UQ) is critical for the deployment of machine learning predictors in real-world scenarios where the data distribution may shift over time (i.e., data ma…
Learning Affine-Equivariant Proximal Operators
Oriel Savir, Zhenghan Fang, Jeremias Sulam
Proximal operators are fundamental across many applications in signal processing and machine learning, including solving ill-posed inverse problems. Recent work has introduced Lear…
Global Sequential Testing for Multi-Stream Auditing
Beepul Bharti, Ambar Pal, Jeremias Sulam
Across many risk-sensitive areas, it is critical to continuously audit machine learning systems as we receive more data to quickly determine if they are performing as designed. Thi…
ProxT2I: Efficient Reward-Guided Text-to-Image Generation via Proximal Diffusion
Zhenghan Fang, Jian Zheng, Qiaozi Gao +2
Diffusion models have emerged as a dominant paradigm for generative modeling across a wide range of domains, including prompt-conditional generation. The vast majority of samplers,…
Learning Regularization Functionals for Inverse Problems: A Comparative Study
Johannes Hertrich, Hok Shing Wong, Alexander Denker +16
In recent years, a variety of learned regularization frameworks for solving inverse problems in imaging have emerged. These offer flexible modeling together with mathematical insig…
Beyond Scores: Proximal Diffusion Models
Zhenghan Fang, Mateo Díaz, Sam Buchanan +1
Diffusion models have quickly become some of the most popular and powerful generative models for high-dimensional data. The key insight that enabled their development was the reali…
Conformal Risk Control for Semantic Uncertainty Quantification in Computed Tomography
Jacopo Teneggi, J Webster Stayman, Jeremias Sulam
Uncertainty quantification is necessary for developers, physicians, and regulatory agencies to build trust in machine learning predictors and improve patient care. Beyond measuring…
Disentangling Safe and Unsafe Corruptions via Anisotropy and Locality
Ramchandran Muthukumar, Ambar Pal, Jeremias Sulam +1
State-of-the-art machine learning systems are vulnerable to small perturbations to their input, where ``small'' is defined according to a threat model that assigns a positive threa…
Sufficient and Necessary Explanations (and What Lies in Between)
Beepul Bharti, Paul Yi, Jeremias Sulam
As complex machine learning models continue to find applications in high-stakes decision-making scenarios, it is crucial that we can explain and understand their predictions. Post-…
Certified Robustness against Sparse Adversarial Perturbations via Data Localization
Ambar Pal, René Vidal, Jeremias Sulam
Recent work in adversarial robustness suggests that natural data distributions are localized, i.e., they place high probability in small volume regions of the input space, and that…