Toyota Technological Institute at Chicago

research

∙ 12/02/2019

Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?

Multiple fairness constraints have been proposed in the literature, moti...

Avrim Blum, et al. ∙

research

∙ 03/24/2020

Deformable Style Transfer

Both geometry and texture are fundamental aspects of visual style. Exist...

Sunnie S. Y. Kim, et al. ∙

research

∙ 04/29/2019

Style Transfer by Relaxed Optimal Transport and Self-Similarity

Style transfer algorithms strive to render the content of one image usin...

Nicholas Kolkin, et al. ∙

research

∙ 12/06/2021

Self-Supervised Camera Self-Calibration from Video

Camera calibration is integral to robotics and computer vision algorithm...

Jiading Fang, et al. ∙

research

∙ 09/26/2019

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Increasing model size when pretraining natural language representations ...

Zhenzhong Lan, et al. ∙

research

∙ 08/28/2019

Fingerspelling recognition in the wild with iterative visual attention

Sign language recognition is a challenging gesture sequence recognition ...

Bowen Shi, et al. ∙

research

∙ 04/04/2020

Pixel Consensus Voting for Panoptic Segmentation

The core of our approach, Pixel Consensus Voting, is a framework for ins...

Haochen Wang, et al. ∙

research

∙ 07/30/2020

Growing Efficient Deep Networks by Structured Continuous Sparsification

We develop an approach to training deep networks while dynamically adjus...

Xin Yuan, et al. ∙

research

∙ 03/08/2022

Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks

The wide adoption and application of Masked language models (MLMs) on se...

Fatemehsadat Mireshghallah, et al. ∙

research

∙ 12/11/2018

Deep Anomaly Detection with Outlier Exposure

It is important to detect and handle anomalous inputs when deploying mac...

Dan Hendrycks, et al. ∙

research

∙ 04/01/2019

Benchmarking Approximate Inference Methods for Neural Structured Prediction

Exact structured inference with neural network scoring functions is comp...

Lifu Tu, et al. ∙

research

∙ 07/16/2019

Natural Adversarial Examples

We introduce natural adversarial examples -- real-world, unmodified, and...

Dan Hendrycks, et al. ∙

research

∙ 12/04/2019

Domain-independent Dominance of Adaptive Methods

From a simplified analysis of adaptive methods, we derive AvaGrad, a new...

Pedro Savarese, et al. ∙

research

∙ 02/28/2022

Setting Fair Incentives to Maximize Improvement

We consider the problem of helping agents improve by setting short-term ...

Saba Ahmadi, et al. ∙

research

∙ 02/18/2020

Is Local SGD Better than Minibatch SGD?

We study local SGD (also known as parallel SGD and federated averaging),...

Blake Woodworth, et al. ∙

research

∙ 09/20/2021

On Generalization in Coreference Resolution

While coreference resolution is defined independently of dataset domain,...

Shubham Toshniwal, et al. ∙

research

∙ 03/25/2019

Recurrent Back-Projection Network for Video Super-Resolution

We proposed a novel architecture for the problem of video super-resoluti...

Muhammad Haris, et al. ∙

research

∙ 09/30/2019

Generating Diverse Story Continuations with Controllable Semantics

We propose a simple and effective modeling framework for controlled gene...

Lifu Tu, et al. ∙

research

∙ 07/10/2021

Layer-wise Analysis of a Self-supervised Speech Representation Model

Recently proposed self-supervised learning approaches have been successf...

Ankita Pasad, et al. ∙

research

∙ 03/14/2022

Multi Stage Screening: Enforcing Fairness and Maximizing Efficiency in a Pre-Existing Pipeline

Consider an actor making selection decisions using a series of classifie...

Avrim Blum, et al. ∙

research

∙ 03/30/2018

Task-Driven Super Resolution: Object Detection in Low-resolution Images

We consider how image super resolution (SR) can contribute to an object ...

Muhammad Haris, et al. ∙

research

∙ 05/30/2018

Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks

Despite existing work on ensuring generalization of neural networks in t...

Behnam Neyshabur, et al. ∙

research

∙ 10/10/2018

End-to-End Content and Plan Selection for Data-to-Text Generation

Learning to generate fluent natural language from structured data with n...

Sebastian Gehrmann, et al. ∙

research

∙ 06/07/2019

Visually Grounded Neural Syntax Acquisition

We present the Visually Grounded Neural Syntax Learner (VG-NSL), an appr...

Haoyue Shi, et al. ∙

research

∙ 09/18/2019

Advancing subgroup fairness via sleeping experts

We study methods for improving fairness to subgroups in settings with ov...

Avrim Blum, et al. ∙

research

∙ 08/04/2020

The Strategic Perceptron

The classical Perceptron algorithm provides a simple and elegant procedu...

Saba Ahmadi, et al. ∙

research

∙ 03/08/2022

Robustly-reliable learners under poisoning attacks

Data poisoning attacks, in which an adversary corrupts a training set wi...

Maria-Florina Balcan, et al. ∙

research

∙ 05/03/2022

Improving In-Context Few-Shot Learning via Self-Supervised Training

Self-supervised pretraining has made few-shot learning possible for many...

Mingda Chen, et al. ∙

research

∙ 11/06/2017

Multilingual Speech Recognition With A Single End-To-End Model

Training a conventional automatic speech recognition (ASR) system to sup...

Shubham Toshniwal, et al. ∙

research

∙ 11/22/2017

From Monte Carlo to Las Vegas: Improving Restricted Boltzmann Machine Training Through Stopping Sets

We propose a Las Vegas transformation of Markov Chain Monte Carlo (MCMC)...

Pedro H. P. Savarese, et al. ∙

research

∙ 11/01/2017

Active Tolerant Testing

In this work, we give the first algorithms for tolerant testing of nontr...

Avrim Blum, et al. ∙

research

∙ 11/23/2016

Multigrid Neural Architectures

We propose a multigrid extension of convolutional neural networks (CNNs)...

Tsung-Wei Ke, et al. ∙

research

∙ 10/07/2016

A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

We consider the two related problems of detecting if an example is miscl...

Dan Hendrycks, et al. ∙

research

∙ 10/09/2017

Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition

We address the problem of automatic American Sign Language fingerspellin...

Bowen Shi, et al. ∙

research

∙ 09/26/2016

Multiplicative LSTM for sequence modelling

We introduce multiplicative LSTM (mLSTM), a recurrent neural network arc...

Ben Krause, et al. ∙

research

∙ 10/05/2017

Semantic keyword spotting by learning from images and speech

We consider the problem of representing semantic concepts in speech by l...

Herman Kamper, et al. ∙

research

∙ 08/01/2016

Early Methods for Detecting Adversarial Images

Many machine learning classifiers are vulnerable to adversarial perturba...

Dan Hendrycks, et al. ∙

research

∙ 07/08/2016

Adjusting for Dropout Variance in Batch Normalization and Weight Initialization

We show how to adjust for the variance introduced by dropout with correc...

Dan Hendrycks, et al. ∙

research

∙ 07/07/2016

Sequence Training and Adaptation of Highway Deep Neural Networks

Highway deep neural network (HDNN) is a type of depth-gated feedforward ...

Liang Lu, et al. ∙

research

∙ 02/13/2016

Signer-independent Fingerspelling Recognition with Deep Neural Network Adaptation

We study the problem of recognition of fingerspelled letter sequences in...

Taehwan Kim, et al. ∙

research

∙ 12/09/2015

Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding

Spectral embedding provides a framework for solving perceptual organizat...

Michael Maire, et al. ∙

research

∙ 04/05/2017

Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition

End-to-end training of deep learning-based models allows for implicit le...

Shubham Toshniwal, et al. ∙

research

∙ 08/11/2017

Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis

We study the problem of acoustic feature learning in the setting where w...

Qingming Tang, et al. ∙

research

∙ 08/07/2017

Training Deep Networks to be Spatially Sensitive

In many computer vision tasks, for example saliency prediction or semant...

Nicholas Kolkin, et al. ∙

research

∙ 05/25/2017

Implicit Regularization in Matrix Factorization

We study implicit regularization when optimizing an underdetermined quad...

Suriya Gunasekar, et al. ∙

research

∙ 02/27/2015

Norm-Based Capacity Control in Neural Networks

We investigate the capacity, convexity and characterization of a general...

Behnam Neyshabur, et al. ∙

research

∙ 11/21/2016

Coherent Dialogue with Attention-based Language Models

We model coherent conversation continuation via RNN-based dialogue model...

Hongyuan Mei, et al. ∙

research

∙ 10/20/2016

Jointly Learning to Align and Convert Graphemes to Phonemes with Neural Attention Models

We propose an attention-enabled encoder-decoder model for the problem of...

Shubham Toshniwal, et al. ∙

research

∙ 10/11/2016

Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation

Modern robotics applications that involve human-robot interaction requir...

Andrea F. Daniele, et al. ∙

research

∙ 02/21/2017

Stochastic Canonical Correlation Analysis

We tightly analyze the sample complexity of CCA, provide a learning algo...

Chao Gao, et al. ∙

Toyota Technological Institute at Chicago

Featured Researchers