Search Results for author: Theodoros Tsiligkaridis

Found 22 papers, 6 papers with code

ERM++: An Improved Baseline for Domain Generalization

no code implementations4 Apr 2023 Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis, Kate Saenko, Bryan A. Plummer

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 Generalization

Domain Adaptation for Time Series Under Feature and Label Shifts

1 code implementation6 Feb 2023 Huan He, Owen Queen, Teddy Koker, Consuelo Cuevas, Theodoros Tsiligkaridis, Marinka Zitnik

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.

Time Series Analysis Unsupervised Domain Adaptation

Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency

1 code implementation17 Jun 2022 Xiang Zhang, Ziyuan Zhao, Theodoros Tsiligkaridis, Marinka Zitnik

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.

Domain Adaptation Electroencephalogram (EEG) +5

Pick up the PACE: Fast and Simple Domain Adaptation via Ensemble Pseudo-Labeling

1 code implementation26 May 2022 Christopher Liao, Theodoros Tsiligkaridis, Brian Kulis

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.

Domain Adaptation

Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration

no code implementations24 Feb 2022 Ryan Soklaski, Michael Yee, Theodoros Tsiligkaridis

Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution.

Image Augmentation

Graph-Guided Network for Irregularly Sampled Multivariate Time Series

2 code implementations ICLR 2022 Xiang Zhang, Marko Zeman, Theodoros Tsiligkaridis, Marinka Zitnik

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.

Time Series Analysis

On Frank-Wolfe Adversarial Training

no code implementations ICML Workshop AML 2021 Theodoros Tsiligkaridis, Jay Roberts

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

no code implementations2 Apr 2021 Theodoros Tsiligkaridis, Athanasios Tsiligkaridis

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.

Data Augmentation Image Classification

Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training

1 code implementation CVPR 2022 Theodoros Tsiligkaridis, Jay Roberts

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

no code implementations30 Nov 2020 Jay Roberts, Theodoros Tsiligkaridis

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

no code implementations19 Oct 2020 Theodoros Tsiligkaridis

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.

Image Classification

Second Order Optimization for Adversarial Robustness and Interpretability

no code implementations10 Sep 2020 Theodoros Tsiligkaridis, Jay Roberts

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.

Adversarial Robustness

Information Aware Max-Norm Dirichlet Networks for Predictive Uncertainty Estimation

no code implementations10 Oct 2019 Theodoros Tsiligkaridis

Precise estimation of uncertainty in predictions for AI systems is a critical factor in ensuring trust and safety.

Reinforcement Learning with Budget-Constrained Nonparametric Function Approximation for Opportunistic Spectrum Access

no code implementations14 Jun 2017 Theodoros Tsiligkaridis, David Romero

Opportunistic spectrum access is one of the emerging techniques for maximizing throughput in congested bands and is enabled by predicting idle slots in spectrum.

reinforcement-learning Reinforcement Learning (RL)

Distributed Probabilistic Bisection Search using Social Learning

no code implementations21 Aug 2016 Athanasios Tsiligkaridis, Theodoros Tsiligkaridis

We present a novel distributed probabilistic bisection algorithm using social learning with application to target localization.

Asynchronous Decentralized 20 Questions for Adaptive Search

no code implementations10 Nov 2015 Theodoros Tsiligkaridis

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

no code implementations NeurIPS 2015 Theodoros Tsiligkaridis, Keith W. Forsythe

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.

Online Clustering

Kronecker Sum Decompositions of Space-Time Data

no code implementations27 Jul 2013 Kristjan Greenewald, Theodoros Tsiligkaridis, Alfred O. Hero III

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

no code implementations12 Feb 2013 Theodoros Tsiligkaridis, Alfred O. Hero III

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.

Vocal Bursts Intensity Prediction

Convergence Properties of Kronecker Graphical Lasso Algorithms

no code implementations3 Apr 2012 Theodoros Tsiligkaridis, Alfred O. Hero III, Shuheng Zhou

The KGlasso algorithm generalizes Glasso, introduced by Yuan and Lin ["Model selection and estimation in the Gaussian graphical model," Biometrika, vol.

Imputation Model Selection

Cannot find the paper you are looking for? You can Submit a new open access paper.