Search Results for author:
Found 38 papers, 6 papers with code
Adaptive Sampling for Estimating Probability Distributions
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.
Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation
Continual learning is inherently a constrained learning problem.
SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection
We theoretically prove the robustness of our algorithm against data and model poisoning attacks in a decentralized linear regression setting.
Decentralized Competing Bandits in Non-Stationary Matching Markets
We propose and analyze a decentralized and asynchronous learning algorithm, namely Decentralized Non-stationary Competing Bandits (\texttt{DNCB}), where the agents play (restrictive) successive elimination type learning algorithms to learn their preference over the arms.
Instance-Dependent Regret Analysis of Kernelized Bandits
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
Confidence intervals are a crucial building block in the analysis of various online learning problems.
Trojan Signatures in DNN Weights
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
Federated learning performed by a decentralized networks of agents is becoming increasingly important with the prevalence of embedded software on autonomous devices.
A Field Guide to Federated Optimization
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection.
Active and Dynamic Beam Tracking UnderStochastic Mobility
We consider the problem of active and sequential beam tracking at mmWave frequencies and above.
Adaptive Sampling for Minimax Fair Classification
Machine learning models trained on uncurated datasets can often end up adversely affecting inputs belonging to underrepresented groups.
Adaptive Sampling for Estimating Distributions: A Bayesian Upper Confidence Bound Approach
A Bayesian variant of the existing upper confidence bound (UCB) based approaches is proposed.
CLEANN: Accelerated Trojan Shield for Embedded Neural Networks
We propose CLEANN, the first end-to-end framework that enables online mitigation of Trojans for embedded Deep Neural Network (DNN) applications.
Low Complexity Sequential Search with Size-Dependent Measurement Noise
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
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
In the contemporary big data realm, Deep Neural Networks (DNNs) are evolving towards more complex architectures to achieve higher inference accuracy.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
ASCAI: Adaptive Sampling for acquiring Compact AI
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.
Adaptive Sampling for Estimating Multiple Probability Distributions
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
We construct and analyze active learning algorithms for the problem of binary classification with abstention.
The Label Complexity of Active Learning from Observational Data
We provably demonstrate that the result of this is an algorithm which is statistically consistent as well as more label-efficient than prior work.
Implicit Label Augmentation on Partially Annotated Clips via Temporally-Adaptive Features Learning
Partially annotated clips contain rich temporal contexts that can complement the sparse key frame annotations in providing supervision for model training.
Decentralized Bayesian Learning over Graphs
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.
Binary Classification with Bounded Abstention Rate
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.
Multiscale Gaussian Process Level Set Estimation
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
We consider the problem of training a machine learning model over a network of nodes in a fully decentralized framework.
Active Learning and CSI Acquisition for mmWave Initial Alignment
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.
SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception
SIGNet is shown to improve upon the state-of-the-art unsupervised learning for depth prediction by 30% (in squared relative error).
Ranked #64 on
Monocular Depth Estimation
on KITTI Eigen split
Efficient Video Understanding via Layered Multi Frame-Rate Analysis
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.
Learning-based attacks in cyber-physical systems
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.
Active Learning with Logged Data
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.
Towards Safe Deep Learning: Unsupervised Defense Against Generic Adversarial Attacks
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
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.
DeepFense: Online Accelerated Defense Against Adversarial Deep Learning
Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems.
Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification
Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them.
Active Learning from Imperfect Labelers
We study active learning where the labeler can not only return incorrect labels but also abstain from labeling.
Adaptive Object Detection Using Adjacency and Zoom Prediction
Compared to methods based on fixed anchor locations, our approach naturally adapts to cases where object instances are sparse and small.
Efficient Object Detection for High Resolution Images
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.
