Search Results for author:
Found 22 papers, 6 papers with code
ERM++: An Improved Baseline for Domain Generalization
We call the resulting method ERM++, and show it significantly improves the performance of DG on five multi-source datasets by over 5% compared to standard ERM, and beats state-of-the-art despite being less computationally expensive.
Domain Adaptation for Time Series Under Feature and Label Shifts
Furthermore, tasks in the source and target domains can have vastly different label distributions, making it difficult for UDA to mitigate label shifts and recognize labels that only exist in the target domain.
Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization
There is extensive interest in metric learning methods for image retrieval.
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency
Experiments against eight state-of-the-art methods show that TF-C outperforms baselines by 15. 4% (F1 score) on average in one-to-one settings (e. g., fine-tuning an EEG-pretrained model on EMG data) and by 8. 4% (precision) in challenging one-to-many settings (e. g., fine-tuning an EEG-pretrained model for either hand-gesture recognition or mechanical fault prediction), reflecting the breadth of scenarios that arise in real-world applications.
Pick up the PACE: Fast and Simple Domain Adaptation via Ensemble Pseudo-Labeling
Domain Adaptation (DA) has received widespread attention from deep learning researchers in recent years because of its potential to improve test accuracy with out-of-distribution labeled data.
Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration
Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution.
Graph-Guided Network for Irregularly Sampled Multivariate Time Series
Here, we introduce RAINDROP, a graph neural network that embeds irregularly sampled and multivariate time series while also learning the dynamics of sensors purely from observational data.
On Frank-Wolfe Adversarial Training
We develop a theoretical framework for adversarial training (AT) with FW optimization (FW-AT) that reveals a geometric connection between the loss landscape and the distortion of $\ell_\infty$ FW attacks (the attack's $\ell_2$ norm).
Diverse Gaussian Noise Consistency Regularization for Robustness and Uncertainty Calibration
In this paper, we propose a diverse Gaussian noise consistency regularization method for improving robustness of image classifiers under a variety of corruptions while still maintaining high clean accuracy.
Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training
We develop a theoretical framework for adversarial training with FW optimization (FW-AT) that reveals a geometric connection between the loss landscape and the $\ell_2$ distortion of $\ell_\infty$ FW attacks.
Ultrasound Diagnosis of COVID-19: Robustness and Explainability
Diagnosis of COVID-19 at point of care is vital to the containment of the global pandemic.
Failure Prediction by Confidence Estimation of Uncertainty-Aware Dirichlet Networks
Reliably assessing model confidence in deep learning and predicting errors likely to be made are key elements in providing safety for model deployment, in particular for applications with dire consequences.
Second Order Optimization for Adversarial Robustness and Interpretability
It is shown that using only a single iteration in our regularizer achieves stronger robustness than prior gradient and curvature regularization schemes, avoids gradient obfuscation, and, with additional iterations, achieves strong robustness with significantly lower training time than AT.
Information Aware Max-Norm Dirichlet Networks for Predictive Uncertainty Estimation
Precise estimation of uncertainty in predictions for AI systems is a critical factor in ensuring trust and safety.
Active query-driven visual search using probabilistic bisection and convolutional neural networks
We present a novel efficient object detection and localization framework based on the probabilistic bisection algorithm.
Reinforcement Learning with Budget-Constrained Nonparametric Function Approximation for Opportunistic Spectrum Access
Opportunistic spectrum access is one of the emerging techniques for maximizing throughput in congested bands and is enabled by predicting idle slots in spectrum.
Distributed Probabilistic Bisection Search using Social Learning
We present a novel distributed probabilistic bisection algorithm using social learning with application to target localization.
Asynchronous Decentralized 20 Questions for Adaptive Search
This paper considers the problem of adaptively searching for an unknown target using multiple agents connected through a time-varying network topology.
Adaptive Low-Complexity Sequential Inference for Dirichlet Process Mixture Models
We develop a sequential low-complexity inference procedure for Dirichlet process mixtures of Gaussians for online clustering and parameter estimation when the number of clusters are unknown a-priori.
Kronecker Sum Decompositions of Space-Time Data
To allow a smooth tradeoff between the reduction in the number of parameters (to reduce estimation variance) and the accuracy of the covariance approximation (affecting estimation bias), we introduce a diagonally loaded modification of the sum of kronecker products representation [1].
Covariance Estimation in High Dimensions via Kronecker Product Expansions
We show that a class of block Toeplitz covariance matrices is approximatable by low separation rank and give bounds on the minimal separation rank $r$ that ensures a given level of bias.
Convergence Properties of Kronecker Graphical Lasso Algorithms
The KGlasso algorithm generalizes Glasso, introduced by Yuan and Lin ["Model selection and estimation in the Gaussian graphical model," Biometrika, vol.
