Search Results for author: Tara Javidi

Found 35 papers, 6 papers with code

Adaptive Sampling for Estimating Probability Distributions

no code implementations ICML 2020 Shubhanshu Shekhar, Tara Javidi, Mohammad Ghavamzadeh

We consider the problem of allocating a fixed budget of samples to a finite set of discrete distributions to learn them uniformly well (minimizing the maximum error) in terms of four common distance measures: $\ell_2^2$, $\ell_1$, $f$-divergence, and separation distance.

Instance-Dependent Regret Analysis of Kernelized Bandits

no code implementations12 Mar 2022 Shubhanshu Shekhar, Tara Javidi

We study the kernelized bandit problem, that involves designing an adaptive strategy for querying a noisy zeroth-order-oracle to efficiently learn about the optimizer of an unknown function $f$ with a norm bounded by $M<\infty$ in a Reproducing Kernel Hilbert Space~(RKHS) associated with a positive definite kernel $K$.

Open Problem: Tight Online Confidence Intervals for RKHS Elements

no code implementations28 Oct 2021 Sattar Vakili, Jonathan Scarlett, Tara Javidi

Confidence intervals are a crucial building block in the analysis of various online learning problems.

online learning reinforcement-learning

Trojan Signatures in DNN Weights

no code implementations7 Sep 2021 Greg Fields, Mohammad Samragh, Mojan Javaheripi, Farinaz Koushanfar, Tara Javidi

Deep neural networks have been shown to be vulnerable to backdoor, or trojan, attacks where an adversary has embedded a trigger in the network at training time such that the model correctly classifies all standard inputs, but generates a targeted, incorrect classification on any input which contains the trigger.

Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian Monte Carlo

no code implementations15 Jul 2021 Vyacheslav Kungurtsev, Adam Cobb, Tara Javidi, Brian Jalaian

Federated learning performed by a decentralized networks of agents is becoming increasingly important with the prevalence of embedded software on autonomous devices.

Federated Learning

Active and Dynamic Beam Tracking UnderStochastic Mobility

no code implementations21 Jun 2021 Nancy Ronquillo, Tara Javidi

We consider the problem of active and sequential beam tracking at mmWave frequencies and above.

Active Learning

Adaptive Sampling for Minimax Fair Classification

no code implementations NeurIPS 2021 Shubhanshu Shekhar, Greg Fields, Mohammad Ghavamzadeh, Tara Javidi

Machine learning models trained on uncurated datasets can often end up adversely affecting inputs belonging to underrepresented groups.

Classification General Classification

Adaptive Sampling for Estimating Distributions: A Bayesian Upper Confidence Bound Approach

no code implementations8 Dec 2020 Dhruva Kartik, Neeraj Sood, Urbashi Mitra, Tara Javidi

A Bayesian variant of the existing upper confidence bound (UCB) based approaches is proposed.

CLEANN: Accelerated Trojan Shield for Embedded Neural Networks

no code implementations4 Sep 2020 Mojan Javaheripi, Mohammad Samragh, Gregory Fields, Tara Javidi, Farinaz Koushanfar

We propose CLEANN, the first end-to-end framework that enables online mitigation of Trojans for embedded Deep Neural Network (DNN) applications.

Dictionary Learning

Low Complexity Sequential Search with Size-Dependent Measurement Noise

no code implementations15 May 2020 Sung-En Chiu, Tara Javidi

Motivated by practical applications such as initial beam alignment in array processing, heavy hitter detection in networking, and visual search in robotics, we consider practically important complexity constraints/metrics: \textit{time complexity}, \textit{computational and memory complexity}, and the complexity of possible query sets in terms of geometry and cardinality.

Multi-Scale Zero-Order Optimization of Smooth Functions in an RKHS

no code implementations11 May 2020 Shubhanshu Shekhar, Tara Javidi

We aim to optimize a black-box function $f:\mathcal{X} \mapsto \mathbb{R}$ under the assumption that $f$ is H\"older smooth and has bounded norm in the RKHS associated with a given kernel $K$.

GeneCAI: Genetic Evolution for Acquiring Compact AI

no code implementations8 Apr 2020 Mojan Javaheripi, Mohammad Samragh, Tara Javidi, Farinaz Koushanfar

In the contemporary big data realm, Deep Neural Networks (DNNs) are evolving towards more complex architectures to achieve higher inference accuracy.

Model Compression

ASCAI: Adaptive Sampling for acquiring Compact AI

no code implementations15 Nov 2019 Mojan Javaheripi, Mohammad Samragh, Tara Javidi, Farinaz Koushanfar

This paper introduces ASCAI, a novel adaptive sampling methodology that can learn how to effectively compress Deep Neural Networks (DNNs) for accelerated inference on resource-constrained platforms.

Model Compression

Adaptive Sampling for Estimating Multiple Probability Distributions

no code implementations28 Oct 2019 Shubhanshu Shekhar, Tara Javidi, Mohammad Ghavamzadeh

We consider the problem of allocating samples to a finite set of discrete distributions in order to learn them uniformly well in terms of four common distance measures: $\ell_2^2$, $\ell_1$, $f$-divergence, and separation distance.

Active Learning for Binary Classification with Abstention

no code implementations1 Jun 2019 Shubhanshu Shekhar, Mohammad Ghavamzadeh, Tara Javidi

We construct and analyze active learning algorithms for the problem of binary classification with abstention.

Active Learning Classification +1

The Label Complexity of Active Learning from Observational Data

1 code implementation NeurIPS 2019 Songbai Yan, Kamalika Chaudhuri, Tara Javidi

We provably demonstrate that the result of this is an algorithm which is statistically consistent as well as more label-efficient than prior work.

Active Learning

Implicit Label Augmentation on Partially Annotated Clips via Temporally-Adaptive Features Learning

no code implementations24 May 2019 Yongxi Lu, Ziyao Tang, Tara Javidi

Partially annotated clips contain rich temporal contexts that can complement the sparse key frame annotations in providing supervision for model training.

Frame Semantic Segmentation

Decentralized Bayesian Learning over Graphs

no code implementations24 May 2019 Anusha Lalitha, Xinghan Wang, Osman Kilinc, Yongxi Lu, Tara Javidi, Farinaz Koushanfar

The proposed algorithm can be viewed as a Bayesian and peer-to-peer variant of federated learning in which each agent keeps a "posterior probability distribution" over a global model parameters.

Bayesian Inference Federated Learning

Binary Classification with Bounded Abstention Rate

no code implementations23 May 2019 Shubhanshu Shekhar, Mohammad Ghavamzadeh, Tara Javidi

We then propose a plug-in classifier that employs unlabeled samples to decide the region of abstention and derive an upper-bound on the excess risk of our classifier under standard \emph{H\"older smoothness} and \emph{margin} assumptions.

Classification General Classification

Multiscale Gaussian Process Level Set Estimation

no code implementations26 Feb 2019 Shubhanshu Shekhar, Tara Javidi

In this paper, the problem of estimating the level set of a black-box function from noisy and expensive evaluation queries is considered.

Peer-to-peer Federated Learning on Graphs

no code implementations31 Jan 2019 Anusha Lalitha, Osman Cihan Kilinc, Tara Javidi, Farinaz Koushanfar

We consider the problem of training a machine learning model over a network of nodes in a fully decentralized framework.

Federated Learning

Active Learning and CSI Acquisition for mmWave Initial Alignment

no code implementations19 Dec 2018 Sung-En Chiu, Nancy Ronquillo, Tara Javidi

In addition, given the knowledge of an optimal directional beamforming vector, large antenna arrays have been shown to overcome both the severe signal attenuation in mmWave as well as the interference problem.

Active Learning

Efficient Video Understanding via Layered Multi Frame-Rate Analysis

no code implementations24 Nov 2018 Ziyao Tang, Yongxi Lu, Tara Javidi

One of the greatest challenges in the design of a real-time perception system for autonomous driving vehicles and drones is the conflicting requirement of safety (high prediction accuracy) and efficiency.

Autonomous Driving Frame +1

Learning-based attacks in cyber-physical systems

no code implementations17 Sep 2018 Mohammad Javad Khojasteh, Anatoly Khina, Massimo Franceschetti, Tara Javidi

In the case of scalar plants, we derive an upper bound on the attacker's deception probability for any measurable control policy when the attacker uses an arbitrary learning algorithm to estimate the system dynamics.

Gaussian Processes

Active Learning with Logged Data

no code implementations ICML 2018 Songbai Yan, Kamalika Chaudhuri, Tara Javidi

We consider active learning with logged data, where labeled examples are drawn conditioned on a predetermined logging policy, and the goal is to learn a classifier on the entire population, not just conditioned on the logging policy.

Active Learning

Towards Safe Deep Learning: Unsupervised Defense Against Generic Adversarial Attacks

no code implementations ICLR 2018 Bita Darvish Rouhani, Mohammad Samragh, Tara Javidi, Farinaz Koushanfar

We introduce a novel automated countermeasure called Parallel Checkpointing Learners (PCL) to thwart the potential adversarial attacks and significantly improve the reliability (safety) of a victim DL model.

Gaussian Process bandits with adaptive discretization

no code implementations5 Dec 2017 Shubhanshu Shekhar, Tara Javidi

In this paper, the problem of maximizing a black-box function $f:\mathcal{X} \to \mathbb{R}$ is studied in the Bayesian framework with a Gaussian Process (GP) prior.

Multi-Armed Bandits

DeepFense: Online Accelerated Defense Against Adversarial Deep Learning

no code implementations8 Sep 2017 Bita Darvish Rouhani, Mohammad Samragh, Mojan Javaheripi, Tara Javidi, Farinaz Koushanfar

Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems.

Active Learning from Imperfect Labelers

no code implementations NeurIPS 2016 Songbai Yan, Kamalika Chaudhuri, Tara Javidi

We study active learning where the labeler can not only return incorrect labels but also abstain from labeling.

Active Learning

Adaptive Object Detection Using Adjacency and Zoom Prediction

1 code implementation CVPR 2016 Yongxi Lu, Tara Javidi, Svetlana Lazebnik

Compared to methods based on fixed anchor locations, our approach naturally adapts to cases where object instances are sparse and small.

Object Detection

Efficient Object Detection for High Resolution Images

no code implementations5 Oct 2015 Yongxi Lu, Tara Javidi

Efficient generation of high-quality object proposals is an essential step in state-of-the-art object detection systems based on deep convolutional neural networks (DCNN) features.

Object Detection

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