Joseph E. Gonzalez

Taxonomizing local versus global structure in neural network loss landscapes

Viewing neural network models in terms of their loss landscapes has a lo...
07/23/2021 ∙ by Yaoqing Yang, et al. ∙ 9 ∙ share

read it
Accelerating Quadratic Optimization with Reinforcement Learning

First-order methods for quadratic optimization such as OSQP are widely u...
07/22/2021 ∙ by Jeffrey Ichnowski, et al. ∙ 10 ∙ share

read it
LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks

Reinforcement learning (RL) algorithms have shown impressive success in ...
07/10/2021 ∙ by Albert Wilcox, et al. ∙ 21 ∙ share

read it
Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies

Robot manipulation for untangling 1D deformable structures such as ropes...
06/29/2021 ∙ by Priya Sundaresan, et al. ∙ 0 ∙ share

read it
Learning Space Partitions for Path Planning

Path planning, the problem of efficiently discovering high-reward trajec...
06/19/2021 ∙ by Kevin Yang, et al. ∙ 5 ∙ share

read it
CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks

Coronary heart disease (CHD) is the leading cause of adult death in the ...
06/14/2021 ∙ by Robert Avram, et al. ∙ 0 ∙ share

read it
Online Learning of Competitive Equilibria in Exchange Economies

The sharing of scarce resources among multiple rational agents is one of...
06/11/2021 ∙ by Wenshuo Guo, et al. ∙ 2 ∙ share

read it
PAC Best Arm Identification Under a Deadline

We study (ϵ, δ)-PAC best arm identification, where a decision-maker must...
06/06/2021 ∙ by Brijen Thananjeyan, et al. ∙ 2 ∙ share

read it
Disentangling Dense Multi-Cable Knots

Disentangling two or more cables requires many steps to remove crossings...
06/04/2021 ∙ by Vainavi Viswanath, et al. ∙ 7 ∙ share

read it
Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines

Despite their ubiquity in core AI fields like natural language processin...
06/02/2021 ∙ by Matthew A. Wright, et al. ∙ 0 ∙ share

read it
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

The increasing size of neural network models has been critical for impro...
04/29/2021 ∙ by Jianfei Chen, et al. ∙ 13 ∙ share

read it
Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models

Humans have a remarkable ability to make decisions by accurately reasoni...
04/21/2021 ∙ by Nicholas Rhinehart, et al. ∙ 0 ∙ share

read it
Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation

Traditional computer vision models are trained to predict a fixed set of...
04/18/2021 ∙ by Ruizhe Cheng, et al. ∙ 0 ∙ share

read it
Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles

We present Pylot, a platform for autonomous vehicle (AV) research and de...
04/16/2021 ∙ by Ionel Gog, et al. ∙ 0 ∙ share

read it
Enhancing the Interactivity of Dataframe Queries by Leveraging Think Time

We propose opportunistic evaluation, a framework for accelerating intera...
03/03/2021 ∙ by Doris Xin, et al. ∙ 0 ∙ share

read it
Online Learning Demands in Max-min Fairness

We describe mechanisms for the allocation of a scarce resource among mul...
12/15/2020 ∙ by Kirthevasan Kandasamy, et al. ∙ 5 ∙ share

read it
Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation

Automation of surgical tasks using cable-driven robots is challenging du...
11/12/2020 ∙ by Samuel Paradis, et al. ∙ 0 ∙ share

read it
Untangling Dense Knots by Learning Task-Relevant Keypoints

Untangling ropes, wires, and cables is a challenging task for robots due...
11/10/2020 ∙ by Jennifer Grannen, et al. ∙ 4 ∙ share

read it
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Nonlinear Scaling with Adaptive Parallelism

We study exploration in stochastic multi-armed bandits when we have acce...
10/31/2020 ∙ by Brijen Thananjeyan, et al. ∙ 11 ∙ share

read it
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones

Safety remains a central obstacle preventing widespread use of RL in the...
10/29/2020 ∙ by Brijen Thananjeyan, et al. ∙ 15 ∙ share

read it
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks

Fully quantized training (FQT), which uses low-bitwidth hardware by quan...
10/27/2020 ∙ by Jianfei Chen, et al. ∙ 0 ∙ share

read it
MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects

We explore learning pixelwise correspondences between images of deformab...
10/09/2020 ∙ by Aditya Ganapathi, et al. ∙ 1 ∙ share

read it
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting

The goal of continual learning (CL) is to learn a sequence of tasks with...
10/04/2020 ∙ by Sayna Ebrahimi, et al. ∙ 9 ∙ share

read it
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

Large-scale labeled training datasets have enabled deep neural networks ...
09/01/2020 ∙ by Sicheng Zhao, et al. ∙ 7 ∙ share

read it
Benchmarking Semi-supervised Federated Learning

Federated learning promises to use the computational power of edge devic...
08/26/2020 ∙ by Zhengming Zhang, et al. ∙ 15 ∙ share

read it
Optimizing Prediction Serving on Low-Latency Serverless Dataflow

Prediction serving systems are designed to provide large volumes of low-...
07/11/2020 ∙ by Vikram Sreekanti, et al. ∙ 0 ∙ share

read it
Boundary thickness and robustness in learning models

Robustness of machine learning models to various adversarial and non-adv...
07/09/2020 ∙ by Yaoqing Yang, et al. ∙ 14 ∙ share

read it
Contrastive Code Representation Learning

Machine-aided programming tools such as automated type predictors and au...
07/09/2020 ∙ by Paras Jain, et al. ∙ 5 ∙ share

read it
BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud

Bird's-eye-view (BEV) is a powerful and widely adopted representation fo...
06/19/2020 ∙ by Mong H. Ng, et al. ∙ 0 ∙ share

read it
Hindsight Logging for Model Training

Due to the long time-lapse between the triggering and detection of a bug...
06/12/2020 ∙ by Rolando Garcia, et al. ∙ 0 ∙ share

read it
SegNBDT: Visual Decision Rules for Segmentation

The black-box nature of neural networks limits model decision interpreta...
06/11/2020 ∙ by Alvin Wan, et al. ∙ 0 ∙ share

read it
Ansor : Generating High-Performance Tensor Programs for Deep Learning

High-performance tensor programs are crucial to guarantee efficient exec...
06/11/2020 ∙ by Lianmin Zheng, et al. ∙ 10 ∙ share

read it
FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function

Neural Architecture Search (NAS) yields state-of-the-art neural networks...
06/03/2020 ∙ by Xiaoliang Dai, et al. ∙ 11 ∙ share

read it
CoVista: A Unified View on Privacy Sensitive Mobile Contact Tracing Effort

Governments around the world have become increasingly frustrated with te...
05/27/2020 ∙ by David Culler, et al. ∙ 0 ∙ share

read it
Thompson Sampling for Linearly Constrained Bandits

We address multi-armed bandits (MAB) where the objective is to maximize ...
04/20/2020 ∙ by Vidit Saxena, et al. ∙ 0 ∙ share

read it
Mechanism Design with Bandit Feedback

We study a multi-round welfare-maximising mechanism design problem, wher...
04/19/2020 ∙ by Kirthevasan Kandasamy, et al. ∙ 4 ∙ share

read it
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Differentiable Neural Architecture Search (DNAS) has demonstrated great ...
04/12/2020 ∙ by Alvin Wan, et al. ∙ 17 ∙ share

read it
NBDT: Neural-Backed Decision Trees

Deep learning is being adopted in settings where accurate and justifiabl...
04/01/2020 ∙ by Alvin Wan, et al. ∙ 0 ∙ share

read it
Learning to Smooth and Fold Real Fabric Using Dense Object Descriptors Trained on Synthetic Color Images

Robotic fabric manipulation is challenging due to the infinite dimension...
03/28/2020 ∙ by Aditya Ganapathi, et al. ∙ 15 ∙ share

read it
Frustratingly Simple Few-Shot Object Detection

Detecting rare objects from a few examples is an emerging problem. Prior...
03/16/2020 ∙ by Xin Wang, et al. ∙ 10 ∙ share

read it
A Fault-Tolerance Shim for Serverless Computing

Serverless computing has grown in popularity in recent years, with an in...
03/12/2020 ∙ by Vikram Sreekanti, et al. ∙ 0 ∙ share

read it
Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data

Robotic manipulation of deformable 1D objects such as ropes, cables, and...
03/03/2020 ∙ by Priya Sundaresan, et al. ∙ 2 ∙ share

read it
ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions

Sample-based learning model predictive control (LMPC) strategies have re...
03/03/2020 ∙ by Brijen Thananjeyan, et al. ∙ 0 ∙ share

read it
Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers

Since hardware resources are limited, the objective of training deep lea...
02/26/2020 ∙ by Zhuohan Li, et al. ∙ 0 ∙ share

read it
SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis

Automatic speech synthesis is a challenging task that is becoming increa...
01/16/2020 ∙ by Bohan Zhai, et al. ∙ 0 ∙ share

read it
Cloudburst: Stateful Functions-as-a-Service

Function-as-a-Service (FaaS) platforms and "serverless" cloud computing ...
01/14/2020 ∙ by Vikram Sreekanti, et al. ∙ 0 ∙ share

read it
Towards Scalable Dataframe Systems

Dataframes are a popular and convenient abstraction to represent, struct...
01/03/2020 ∙ by Devin Petersohn, et al. ∙ 0 ∙ share

read it
Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization

Modern neural networks are increasingly bottlenecked by the limited capa...
10/07/2019 ∙ by Paras Jain, et al. ∙ 12 ∙ share

read it
Helen: Maliciously Secure Coopetitive Learning for Linear Models

Many organizations wish to collaboratively train machine learning models...
07/16/2019 ∙ by Wenting Zheng, et al. ∙ 0 ∙ share

read it
On-Policy Robot Imitation Learning from a Converging Supervisor

Existing on-policy imitation learning algorithms, such as DAgger, assume...
07/08/2019 ∙ by Ashwin Balakrishna, et al. ∙ 6 ∙ share

read it

Joseph E. Gonzalez

Featured Co-authors