Search Results for author:
Found 42 papers, 15 papers with code
Axiomatic Explainer Globalness via Optimal Transport
Explainability methods are often challenging to evaluate and compare.
ADAPT to Robustify Prompt Tuning Vision Transformers
The performance of deep models, including Vision Transformers, is known to be vulnerable to adversarial attacks.
Multiverse at the Edge: Interacting Real World and Digital Twins for Wireless Beamforming
To achieve this, we go beyond instantiating a single twin and propose the 'Multiverse' paradigm, with several possible digital twins attempting to capture the real world at different levels of fidelity.
DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Rehearsal-based approaches are a mainstay of continual learning (CL).
Explanations of Black-Box Models based on Directional Feature Interactions
As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent.
Geometry of Score Based Generative Models
We demonstrate that looking from geometric perspective enables us to answer many of these questions and provide new interpretations to some known results.
Divide and Compose with Score Based Generative Models
Towards the direction of having more control over image manipulation and conditional generation, we propose to learn image components in an unsupervised manner so that we can compose those components to generate and manipulate images in informed manner.
High-precision regressors for particle physics
Since the necessary number of data points per simulation is on the order of $10^9$ - $10^{12}$, machine learning regressors can be used in place of physics simulators to significantly reduce this computational burden.
SAIF: Sparse Adversarial and Imperceptible Attack Framework
Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal.
QueryForm: A Simple Zero-shot Form Entity Query Framework
Zero-shot transfer learning for document understanding is a crucial yet under-investigated scenario to help reduce the high cost involved in annotating document entities.
Pruning Adversarially Robust Neural Networks without Adversarial Examples
Adversarial pruning compresses models while preserving robustness.
Boundary-Aware Uncertainty for Feature Attribution Explainers
In this work we propose the Gaussian Process Explanation UnCertainty (GPEC) framework, which generates a unified uncertainty estimate combining decision boundary-aware uncertainty with explanation function approximation uncertainty.
SparCL: Sparse Continual Learning on the Edge
SparCL achieves both training acceleration and accuracy preservation through the synergy of three aspects: weight sparsity, data efficiency, and gradient sparsity.
Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions
We provide lower bound guarantees on the astuteness of a variety of explainers (e. g., SHAP, RISE, CXPlain) given the Lipschitzness of the prediction function.
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting.
Deep Layer-wise Networks Have Closed-Form Weights
There is currently a debate within the neuroscience community over the likelihood of the brain performing backpropagation (BP).
Deep Learning on Multimodal Sensor Data at the Wireless Edge for Vehicular Network
Beam selection for millimeter-wave links in a vehicular scenario is a challenging problem, as an exhaustive search among all candidate beam pairs cannot be assuredly completed within short contact times.
Learning to Prompt for Continual Learning
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge.
Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection
There are limited works showing the efficacy of unsupervised Out-of-Distribution (OOD) methods on complex medical data.
Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Space
To achieve this objective, we 1) present a novel construction of the discriminator in the Reproducing Kernel Hilbert Space (RKHS), 2) theoretically relate the error probability bound of the KL estimates to the complexity of the discriminator in the RKHS space, 3) present a scalable way to control the complexity (RKHS norm) of the discriminator for a reliable estimation of KL divergence, and 4) prove the consistency of the proposed estimator.
Deep Bayesian Unsupervised Lifelong Learning
We develop a fully Bayesian inference framework for ULL with a novel end-to-end Deep Bayesian Unsupervised Lifelong Learning (DBULL) algorithm, which can progressively discover new clusters without forgetting the past with unlabelled data while learning latent representations.
Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness
We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier.
On the Sample Complexity of Rank Regression from Pairwise Comparisons
We consider a rank regression setting, in which a dataset of $N$ samples with features in $\mathbb{R}^d$ is ranked by an oracle via $M$ pairwise comparisons.
Machine Learning on Camera Images for Fast mmWave Beamforming
Perfect alignment in chosen beam sectors at both transmit- and receive-nodes is required for beamforming in mmWave bands.
Learn-Prune-Share for Lifelong Learning
In lifelong learning, we wish to maintain and update a model (e. g., a neural network classifier) in the presence of new classification tasks that arrive sequentially.
Open-World Class Discovery with Kernel Networks
We study an Open-World Class Discovery problem in which, given labeled training samples from old classes, we need to discover new classes from unlabeled test samples.
Instance-wise Feature Grouping
Moreover, the features that belong to each group, and the important feature groups may vary per sample.
Kernel Dependence Network
We propose a greedy strategy to spectrally train a deep network for multi-class classification.
Deep Layer-wise Networks Have Closed-Form Weights
There is currently a debate within the neuroscience community over the likelihood of the brain performing backpropagation (BP).
Deep Markov Spatio-Temporal Factorization
This results in a flexible family of hierarchical deep generative factor analysis models that can be extended to perform time series clustering or perform factor analysis in the presence of a control signal.
Weighting Is Worth the Wait: Bayesian Optimization with Importance Sampling
Casting hyperparameter search as a multi-task Bayesian optimization problem over both hyperparameters and importance sampling design achieves the best of both worlds: by learning a parameterization of IS that trades-off evaluation complexity and quality, we improve upon Bayesian optimization state-of-the-art runtime and final validation error across a variety of datasets and complex neural architectures.
Segmentation of Cellular Patterns in Confocal Images of Melanocytic Lesions in vivo via a Multiscale Encoder-Decoder Network (MED-Net)
We trained and tested our model on non-overlapping partitions of 117 reflectance confocal microscopy (RCM) mosaics of melanocytic lesions, an extensive dataset for this application, collected at four clinics in the US, and two in Italy.
Solving Interpretable Kernel Dimensionality Reduction
While KDR methods can be easily solved by keeping the most dominant eigenvectors of the kernel matrix, its features are no longer easy to interpret.
Solving Interpretable Kernel Dimension Reduction
While KDR methods can be easily solved by keeping the most dominant eigenvectors of the kernel matrix, its features are no longer easy to interpret.
Spectral Non-Convex Optimization for Dimension Reduction with Hilbert-Schmidt Independence Criterion
The Hilbert Schmidt Independence Criterion (HSIC) is a kernel dependence measure that has applications in various aspects of machine learning.
Deep Kernel Learning for Clustering
We propose a deep learning approach for discovering kernels tailored to identifying clusters over sample data.
Neural Topographic Factor Analysis for fMRI Data
Neuroimaging studies produce gigabytes of spatio-temporal data for a small number of participants and stimuli.
Accelerated Experimental Design for Pairwise Comparisons
Pairwise comparison labels are more informative and less variable than class labels, but generating them poses a challenge: their number grows quadratically in the dataset size.
Deep feature transfer between localization and segmentation tasks
In this paper, we propose a new pre-training scheme for U-net based image segmentation.
Structured Disentangled Representations
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner.
Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning
Furthermore, we find that the lognormal distribution, which can handle skewed distributions, produces quality uncertainty estimates at the extremes.
Evaluating Crowdsourcing Participants in the Absence of Ground-Truth
Given a supervised/semi-supervised learning scenario where multiple annotators are available, we consider the problem of identification of adversarial or unreliable annotators.
