Matthew Nokleby
YOU?
Author Swipe
View article: Ontology-Guided Knowledge Graph Retrieval for Multi-Hop and Cross-Granularity Store Fulfillment Queries
Ontology-Guided Knowledge Graph Retrieval for Multi-Hop and Cross-Granularity Store Fulfillment Queries Open
View article: Information-Theoretic Bayes Risk Lower Bounds for Realizable Models
Information-Theoretic Bayes Risk Lower Bounds for Realizable Models Open
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 rate-distortion function of the model parameters bounds the re…
View article: Anytime MiniBatch: Exploiting Stragglers in Online Distributed Optimization
Anytime MiniBatch: Exploiting Stragglers in Online Distributed Optimization Open
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 complete their assigned tasks in each computational epoch …
View article: Anytime MiniBatch: Exploiting Stragglers in Online Distributed\n Optimization
Anytime MiniBatch: Exploiting Stragglers in Online Distributed\n Optimization Open
Distributed optimization is vital in solving large-scale machine learning\nproblems. A widely-shared feature of distributed optimization techniques is the\nrequirement that all nodes complete their assigned tasks in each computational\nepo…
View article: Learning Furniture Compatibility with Graph Neural Networks
Learning Furniture Compatibility with Graph Neural Networks Open
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 based on siamese networks which evaluate pairwise compatibil…
View article: An Effective Label Noise Model for DNN Text Classification
An Effective Label Noise Model for DNN Text Classification Open
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 classification models with label noise have received much atte…
View article: A Robotic Recording and Playback Platform for Training Surgeons and Learning Autonomous Behaviors Using the da Vinci Surgical System
A Robotic Recording and Playback Platform for Training Surgeons and Learning Autonomous Behaviors Using the da Vinci Surgical System Open
This paper describes a recording and playback system developed using a da Vinci Standard Surgical System and research kit. The system records stereo laparoscopic videos, robot arm joint angles, and surgeon–console interactions in a synchro…
View article: An Effective Label Noise Model for
An Effective Label Noise Model for Open
Ishan Jindal, Daniel Pressel, Brian Lester, Matthew Nokleby. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). …
View article: Optimizing Taxi Carpool Policies via Reinforcement Learning and Spatio-Temporal Mining
Optimizing Taxi Carpool Policies via Reinforcement Learning and Spatio-Temporal Mining Open
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 required to fulfill the given amount of trip demand. For this …
View article: Tensor Matched Kronecker-Structured Subspace Detection for Missing\n Information
Tensor Matched Kronecker-Structured Subspace Detection for Missing\n Information Open
We consider the problem of detecting whether a tensor signal having many\nmissing entities lies within a given low dimensional Kronecker-Structured (KS)\nsubspace. This is a matched subspace detection problem. Tensor matched subspace\ndete…
View article: Tensor Matched Kronecker-Structured Subspace Detection for Missing Information
Tensor Matched Kronecker-Structured Subspace Detection for Missing Information Open
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 subspace detection problem. Tensor matched subspace detecti…
View article: Information Bottleneck Methods for Distributed Learning
Information Bottleneck Methods for Distributed Learning Open
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 learning problem. We formalize this as a rate-distortion pr…
View article: Stochastic Optimization From Distributed Streaming Data in Rate-Limited Networks
Stochastic Optimization From Distributed Streaming Data in Rate-Limited Networks Open
Motivated by machine learning applications in networks of sensors,\ninternet-of-things (IoT) devices, and autonomous agents, we propose techniques\nfor distributed stochastic convex learning from high-rate data streams. The\nsetup involves…
View article: Classification and Representation via Separable Subspaces: Performance Limits and Algorithms
Classification and Representation via Separable Subspaces: Performance Limits and Algorithms Open
We study the classification performance of Kronecker-structured models in two\nasymptotic regimes and developed an algorithm for separable, fast and compact\nK-S dictionary learning for better classification and representation of\nmultidim…
View article: Multi-scale Spectrum Sensing in 5G Cognitive Networks.
Multi-scale Spectrum Sensing in 5G Cognitive Networks. Open
A multi-scale approach to spectrum sensing is proposed to overcome the huge energy cost of acquiring full network state information over 5G cognitive networks. Secondary users (SUs) estimate the local spectrum occupancies and aggregate the…
View article: Multi-Scale Spectrum Sensing in Dense Multi-Cell Cognitive Networks
Multi-Scale Spectrum Sensing in Dense Multi-Cell Cognitive Networks Open
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 networks. Secondary users (SUs) estimate the local spectrum occu…
View article: A Unified Neural Network Approach for Estimating Travel Time and Distance for a Taxi Trip
A Unified Neural Network Approach for Estimating Travel Time and Distance for a Taxi Trip Open
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 management. Using the NYC taxi dataset, which contains taxi …
View article: Improving short-term electricity price forecasting using day-ahead LMP with ARIMA models
Improving short-term electricity price forecasting using day-ahead LMP with ARIMA models Open
Short-term electricity price forecasting has become important for demand side\nmanagement and power generation scheduling. Especially as the electricity\nmarket becomes more competitive, a more accurate price prediction than the\nday-ahead…
View article: Learning Deep Networks from Noisy Labels with Dropout Regularization
Learning Deep Networks from Noisy Labels with Dropout Regularization Open
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 exhibit poor performance. We present a simple, effective techni…
View article: Multi-scale Spectrum Sensing in Small-Cell mm-Wave Cognitive Wireless Networks
Multi-scale Spectrum Sensing in Small-Cell mm-Wave Cognitive Wireless Networks Open
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 state information, a hierarchical scheme is proposed, base…
View article: Multi-scale Spectrum Sensing in Small-Cell mm-Wave Cognitive Wireless\n Networks
Multi-scale Spectrum Sensing in Small-Cell mm-Wave Cognitive Wireless\n Networks Open
In this paper, a multi-scale approach to spectrum sensing in cognitive\ncellular networks is proposed. In order to overcome the huge cost incurred in\nthe acquisition of full network state information, a hierarchical scheme is\nproposed, b…
View article: Low-Dimensional Shaping for High-Dimensional Lattice Codes
Low-Dimensional Shaping for High-Dimensional Lattice Codes Open
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 of integers to the dithered Voronoi integers, which are di…
View article: Rate-Distortion Bounds on Bayes Risk in Supervised Learning
Rate-Distortion Bounds on Bayes Risk in Supervised Learning Open
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 average $L_p$ distance between the learned classifier and the t…