64 citations · 222 across the 17 of their papers we have counts for
20 papers
Information-Theoretic Bayes Risk Lower Bounds for Realizable Models
Matthew Nokleby, Ahmad Beirami
We derive information-theoretic lower bounds on the Bayes risk and generalization error of realizable machine learning models. In particular, we employ an analysis in which the rat…
Anytime MiniBatch: Exploiting Stragglers in Online Distributed Optimization
Nuwan Ferdinand, Haider Al-Lawati, Stark C. Draper +1
Distributed optimization is vital in solving large-scale machine learning problems. A widely-shared feature of distributed optimization techniques is the requirement that all nodes…
Scaling-up Distributed Processing of Data Streams for Machine Learning
Matthew Nokleby, Haroon Raja, Waheed U. Bajwa
Emerging applications of machine learning in numerous areas involve continuous gathering of and learning from streams of data. Real-time incorporation of streaming data into the le…
Learning Furniture Compatibility with Graph Neural Networks
Luisa F. Polania, Mauricio Flores, Yiran Li +1
We propose a graph neural network (GNN) approach to the problem of predicting the stylistic compatibility of a set of furniture items from images. While most existing results are b…
An Effective Label Noise Model for DNN Text Classification
Ishan Jindal, Daniel Pressel, Brian Lester +1
Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image cla…
Optimizing Taxi Carpool Policies via Reinforcement Learning and Spatio-Temporal Mining
Ishan Jindal, Zhiwei Qin, Xuewen Chen +2
In this paper, we develop a reinforcement learning (RL) based system to learn an effective policy for carpooling that maximizes transportation efficiency so that fewer cars are req…
Information Bottleneck Methods for Distributed Learning
Parinaz Farajiparvar, Ahmad Beirami, Matthew Nokleby
We study a distributed learning problem in which Alice sends a compressed distillation of a set of training data to Bob, who uses the distilled version to best solve an associated…
Tensor Matched Kronecker-Structured Subspace Detection for Missing Information
Ishan Jindal, Matthew Nokleby
We consider the problem of detecting whether a tensor signal having many missing entities lies within a given low dimensional Kronecker-Structured (KS) subspace. This is a matched…
Multi-Scale Spectrum Sensing in Dense Multi-Cell Cognitive Networks
Nicolo Michelusi, Matthew Nokleby, Urbashi Mitra +1
Multi-scale spectrum sensing is proposed to overcome the cost of full network state information on the spectrum occupancy of primary users (PUs) in dense multi-cell cognitive netwo…
Improving Short-Term Electricity Price Forecasting Using Day-Ahead LMP with ARIMA Models
Zhongyang Zhao, Caisheng Wang, Matthew Nokleby +1
Short-term electricity price forecasting has become important for demand side management and power generation scheduling. Especially as the electricity market becomes more competit…
A Unified Neural Network Approach for Estimating Travel Time and Distance for a Taxi Trip
Ishan Jindal, Tony, Qin +3
In building intelligent transportation systems such as taxi or rideshare services, accurate prediction of travel time and distance is crucial for customer experience and resource m…
Learning Deep Networks from Noisy Labels with Dropout Regularization
Ishan Jindal, Matthew Nokleby, Xuewen Chen
Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhi…
Classification and Representation via Separable Subspaces: Performance Limits and Algorithms
Ishan Jindal, Matthew Nokleby
We study the classification performance of Kronecker-structured models in two asymptotic regimes and developed an algorithm for separable, fast and compact K-S dictionary learning…
Stochastic Optimization from Distributed, Streaming Data in Rate-limited Networks
Matthew Nokleby, Waheed U. Bajwa
Motivated by machine learning applications in networks of sensors, internet-of-things (IoT) devices, and autonomous agents, we propose techniques for distributed stochastic convex…
Multi-scale Spectrum Sensing in Small-Cell mm-Wave Cognitive Wireless Networks
Nicolo Michelusi, Matthew Nokleby, Urbashi Mitra +1
In this paper, a multi-scale approach to spectrum sensing in cognitive cellular networks is proposed. In order to overcome the huge cost incurred in the acquisition of full network…
Low-Dimensional Shaping for High-Dimensional Lattice Codes
Nuwan S. Ferdinand, Brian M. Kurkoski, Matthew Nokleby +1
We propose two low-complexity lattice code constructions that have competitive coding and shaping gains. The first construction, named systematic Voronoi shaping, maps short blocks…
Rate-Distortion Bounds on Bayes Risk in Supervised Learning
Matthew Nokleby, Ahmad Beirami, Robert Calderbank
We present an information-theoretic framework for bounding the number of labeled samples needed to train a classifier in a parametric Bayesian setting. We derive bounds on the aver…
Discrimination on the Grassmann Manifold: Fundamental Limits of Subspace Classifiers
Matthew Nokleby, Miguel Rodrigues, Robert Calderbank
We present fundamental limits on the reliable classification of linear and affine subspaces from noisy, linear features. Drawing an analogy between discrimination among subspaces a…
Toward Resource-Optimal Consensus over the Wireless Medium
Matthew Nokleby, Waheed U. Bajwa, Robert Calderbank +1
We carry out a comprehensive study of the resource cost of averaging consensus in wireless networks. Most previous approaches suppose a graphical network, which abstracts away cruc…
Cooperative Compute-and-Forward
Matthew Nokleby, Behnaam Aazhang
We examine the benefits of user cooperation under compute-and-forward. Much like in network coding, receivers in a compute-and-forward network recover finite-field linear combinati…