Search Results for author:
Found 36 papers, 17 papers with code
Multiaccuracy and Multicalibration via Proxy Groups
Additionally, we show that adjusting models to satisfy multiaccuracy and multicalibration across proxy-sensitive attributes can significantly mitigate these violations for the true, but unknown, sensitive groups.
Conformal Risk Control for Semantic Uncertainty Quantification in Computed Tomography
Uncertainty quantification is necessary for developers, physicians, and regulatory agencies to build trust in machine learning predictors and improve patient care.
Disentangling Safe and Unsafe Corruptions via Anisotropy and Locality
The proposed threat model measures the threat of a perturbation via its alignment with \textit{unsafe directions}, defined as directions in the input space along which a perturbation of sufficient magnitude changes the ground truth class label.
Sufficient and Necessary Explanations (and What Lies in Between)
We demonstrate how these two types of explanations, albeit intuitive and simple, can fall short in providing a complete picture of which features a model finds important.
Pivotal Auto-Encoder via Self-Normalizing ReLU
Leveraging the transform modeling interpretation, we propose an optimization problem that leads to a predictive model invariant to the noise level at test time.
I Bet You Did Not Mean That: Testing Semantic Importance via Betting
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.
Certified Robustness against Sparse Adversarial Perturbations via Data Localization
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 this property can be utilized for designing classifiers with improved robustness guarantees for $\ell_2$-bounded perturbations.
What's in a Prior? Learned Proximal Networks for Inverse Problems
Proximal operators are ubiquitous in inverse problems, commonly appearing as part of algorithmic strategies to regularize problems that are otherwise ill-posed.
Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
The susceptibility of modern machine learning classifiers to adversarial examples has motivated theoretical results suggesting that these might be unavoidable.
Sparsity-aware generalization theory for deep neural networks
In this paper, we present a new approach to analyzing generalization for deep feed-forward ReLU networks that takes advantage of the degree of sparsity that is achieved in the hidden layer activations.
Understanding Noise-Augmented Training for Randomized Smoothing
This method relies on taking a majority vote of any base classifier over multiple noise-perturbed inputs to obtain a smoothed classifier, and it remains the tool of choice to certify deep and complex neural network models.
How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control
Score-based generative modeling, informally referred to as diffusion models, continue to grow in popularity across several important domains and tasks.
Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT
We find that strong supervision (i. e., learning with local image-level annotations) and weak supervision (i. e., learning with only global examination-level labels) achieve comparable performance in examination-level hemorrhage detection (the task of selecting the images in an examination that show signs of hemorrhage) as well as in image-level hemorrhage detection (highlighting those signs within the selected images).
DeepSTI: Towards Tensor Reconstruction using Fewer Orientations in Susceptibility Tensor Imaging
Experimental results using both simulation and in vivo human data demonstrate great improvement over state-of-the-art algorithms in terms of the reconstructed tensor image, principal eigenvector maps and tractography results, while allowing for tensor reconstruction with MR phase measured at much less than six different orientations.
SHAP-XRT: The Shapley Value Meets Conditional Independence Testing
As a result, we further our understanding of Shapley-based explanation methods from a novel perspective and characterize the conditions under which one can make statistically valid claims about feature importance via the Shapley value.
Adversarial robustness of sparse local Lipschitz predictors
This work studies the adversarial robustness of parametric functions composed of a linear predictor and a non-linear representation map.
Entrywise Recovery Guarantees for Sparse PCA via Sparsistent Algorithms
Sparse Principal Component Analysis (PCA) is a prevalent tool across a plethora of subfields of applied statistics.
Deciphering antibody affinity maturation with language models and weakly supervised learning
Understanding the composition of an individual's immune repertoire can provide insights into this process and reveal potential therapeutic antibodies.
Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images
Annotating cancerous regions in whole-slide images (WSIs) of pathology samples plays a critical role in clinical diagnosis, biomedical research, and machine learning algorithms development.
A Geometric Analysis of Neural Collapse with Unconstrained Features
In contrast to existing landscape analysis for deep neural networks which is often disconnected from practice, our analysis of the simplified model not only does it explain what kind of features are learned in the last layer, but it also shows why they can be efficiently optimized in the simplified settings, matching the empirical observations in practical deep network architectures.
Fast Hierarchical Games for Image Explanations
As modern complex neural networks keep breaking records and solving harder problems, their predictions also become less and less intelligible.
Learning to solve TV regularised problems with unrolled algorithms
In this paper, we accelerate such iterative algorithms by unfolding proximal gradient descent solvers in order to learn their parameters for 1D TV regularized problems.
Adversarial Robustness of Supervised Sparse Coding
Several recent results provide theoretical insights into the phenomena of adversarial examples.
Learning to solve TV regularized problems with unrolled algorithms
In this paper, we accelerate such iterative algorithms by unfolding proximal gradient descent solvers in order to learn their parameters for 1D TV regularized problems.
Learned Proximal Networks for Quantitative Susceptibility Mapping
More importantly, this framework is believed to be the first deep learning QSM approach that can naturally handle an arbitrary number of phase input measurements without the need for any ad-hoc rotation or re-training.
Deep Learning in Protein Structural Modeling and Design
Deep learning is catalyzing a scientific revolution fueled by big data, accessible toolkits, and powerful computational resources, impacting many fields including protein structural modeling.
Recovery and Generalization in Over-Realized Dictionary Learning
We thoroughly demonstrate this observation in practice and provide an analysis of this phenomenon by tying recovery measures to generalization bounds.
Conformal Symplectic and Relativistic Optimization
Arguably, the two most popular accelerated or momentum-based optimization methods in machine learning are Nesterov's accelerated gradient and Polyaks's heavy ball, both corresponding to different discretizations of a particular second order differential equation with friction.
A Local Block Coordinate Descent Algorithm for the Convolutional Sparse Coding Model
The Convolutional Sparse Coding (CSC) model has recently gained considerable traction in the signal and image processing communities.
MMSE Approximation For Sparse Coding Algorithms Using Stochastic Resonance
The proposed method adds controlled noise to the input and estimates a sparse representation from the perturbed signal.
On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks
Parsimonious representations are ubiquitous in modeling and processing information.
Adversarial Noise Attacks of Deep Learning Architectures -- Stability Analysis via Sparse Modeled Signals
Despite their impressive performance, deep convolutional neural networks (CNNs) have been shown to be sensitive to small adversarial perturbations.
Multi-Layer Sparse Coding: The Holistic Way
The recently proposed multi-layer sparse model has raised insightful connections between sparse representations and convolutional neural networks (CNN).
Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning
We show that the training of the filters is essential to allow for non-trivial signals in the model, and we derive an online algorithm to learn the dictionaries from real data, effectively resulting in cascaded sparse convolutional layers.
Convolutional Dictionary Learning via Local Processing
Convolutional Sparse Coding (CSC) is an increasingly popular model in the signal and image processing communities, tackling some of the limitations of traditional patch-based sparse representations.
Trainlets: Dictionary Learning in High Dimensions
Sparse representations has shown to be a very powerful model for real world signals, and has enabled the development of applications with notable performance.
