128 citations · 615 across the 36 of their papers we have counts for
38 papers
Direct Preference Optimization for Adaptive Concept-based Explanations
Jacopo Teneggi, Zhenzhen Wang, Paul H. Yi +2
Concept-based explanation methods aim at making machine learning models more transparent by finding the most important semantic features of an input (e.g., colors, patterns, shapes…
Multiaccuracy and Multicalibration via Proxy Groups
Beepul Bharti, Mary Versa Clemens-Sewall, Paul H. Yi +1
As the use of predictive machine learning algorithms increases in high-stakes decision-making, it is imperative that these algorithms are fair across sensitive groups. However, mea…
Pivotal Auto-Encoder via Self-Normalizing ReLU
Nelson Goldenstein, Jeremias Sulam, Yaniv Romano
Sparse auto-encoders are useful for extracting low-dimensional representations from high-dimensional data. However, their performance degrades sharply when the input noise at test…
I Bet You Did Not Mean That: Testing Semantic Importance via Betting
Jacopo Teneggi, Jeremias Sulam
Recent works have extended notions of feature importance to semantic concepts that are inherently interpretable to the users interacting with a black-box predictive model. Yet, pre…
What's in a Prior? Learned Proximal Networks for Inverse Problems
Zhenghan Fang, Sam Buchanan, Jeremias Sulam
Proximal operators are ubiquitous in inverse problems, commonly appearing as part of algorithmic strategies to regularize problems that are otherwise ill-posed. Modern deep learnin…
Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
Ambar Pal, Jeremias Sulam, René Vidal
The susceptibility of modern machine learning classifiers to adversarial examples has motivated theoretical results suggesting that these might be unavoidable. However, these resul…
Sparsity-aware generalization theory for deep neural networks
Ramchandran Muthukumar, Jeremias Sulam
Deep artificial neural networks achieve surprising generalization abilities that remain poorly understood. In this paper, we present a new approach to analyzing generalization for…
Understanding Noise-Augmented Training for Randomized Smoothing
Ambar Pal, Jeremias Sulam
Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies…
Fourier Diffusion Models: A Method to Control MTF and NPS in Score-Based Stochastic Image Generation
Matthew Tivnan, Jacopo Teneggi, Tzu-Cheng Lee +6
Score-based stochastic denoising models have recently been demonstrated as powerful machine learning tools for conditional and unconditional image generation. The existing methods…
How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control
Jacopo Teneggi, Matthew Tivnan, J. Webster Stayman +1
Score-based generative modeling, informally referred to as diffusion models, continue to grow in popularity across several important domains and tasks. While they provide high-qual…
Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT
Jacopo Teneggi, Paul H. Yi, Jeremias Sulam
Modern machine learning pipelines, in particular those based on deep learning (DL) models, require large amounts of labeled data. For classification problems, the most common learn…
DeepSTI: Towards Tensor Reconstruction using Fewer Orientations in Susceptibility Tensor Imaging
Zhenghan Fang, Kuo-Wei Lai, Peter van Zijl +2
Susceptibility tensor imaging (STI) is an emerging magnetic resonance imaging technique that characterizes the anisotropic tissue magnetic susceptibility with a second-order tensor…
Estimating and Controlling for Equalized Odds via Sensitive Attribute Predictors
Beepul Bharti, Paul Yi, Jeremias Sulam
As the use of machine learning models in real world high-stakes decision settings continues to grow, it is highly important that we are able to audit and control for any potential…
SHAP-XRT: The Shapley Value Meets Conditional Independence Testing
Jacopo Teneggi, Beepul Bharti, Yaniv Romano +1
The complex nature of artificial neural networks raises concerns on their reliability, trustworthiness, and fairness in real-world scenarios. The Shapley value -- a solution concep…
Entrywise Recovery Guarantees for Sparse PCA via Sparsistent Algorithms
Joshua Agterberg, Jeremias Sulam
Sparse Principal Component Analysis (PCA) is a prevalent tool across a plethora of subfields of applied statistics. While several results have characterized the recovery error of t…
Adversarial robustness of sparse local Lipschitz predictors
Ramchandran Muthukumar, Jeremias Sulam
This work studies the adversarial robustness of parametric functions composed of a linear predictor and a non-linear representation map. % that satisfies certain stability conditio…
Deciphering antibody affinity maturation with language models and weakly supervised learning
Jeffrey A. Ruffolo, Jeffrey J. Gray, Jeremias Sulam
In response to pathogens, the adaptive immune system generates specific antibodies that bind and neutralize foreign antigens. Understanding the composition of an individual's immun…
Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images
Zhenzhen Wang, Carla Saoud, Sintawat Wangsiricharoen +3
Annotating cancerous regions in whole-slide images (WSIs) of pathology samples plays a critical role in clinical diagnosis, biomedical research, and machine learning algorithms dev…
A Geometric Analysis of Neural Collapse with Unconstrained Features
Zhihui Zhu, Tianyu Ding, Jinxin Zhou +4
We provide the first global optimization landscape analysis of -- an intriguing empirical phenomenon that arises in the last-layer classifiers and features of ne…
Fast Hierarchical Games for Image Explanations
Jacopo Teneggi, Alexandre Luster, Jeremias Sulam
As modern complex neural networks keep breaking records and solving harder problems, their predictions also become less and less intelligible. The current lack of interpretability…
Learning to solve TV regularized problems with unrolled algorithms
Hamza Cherkaoui, Jeremias Sulam, Thomas Moreau
Total Variation (TV) is a popular regularization strategy that promotes piece-wise constant signals by constraining the -norm of the first order derivative of the estimated…
Adversarial Robustness of Supervised Sparse Coding
Jeremias Sulam, Ramchandran Muthukumar, Raman Arora
Several recent results provide theoretical insights into the phenomena of adversarial examples. Existing results, however, are often limited due to a gap between the simplicity of…
Learned Proximal Networks for Quantitative Susceptibility Mapping
Kuo-Wei Lai, Manisha Aggarwal, Peter van Zijl +2
Quantitative Susceptibility Mapping (QSM) estimates tissue magnetic susceptibility distributions from Magnetic Resonance (MR) phase measurements by solving an ill-posed dipole inve…
Deep Learning in Protein Structural Modeling and Design
Wenhao Gao, Sai Pooja Mahajan, Jeremias Sulam +1
Deep learning is catalyzing a scientific revolution fueled by big data, accessible toolkits, and powerful computational resources, impacting many fields including protein structura…