
-
Online Learning Demands in Max-min Fairness
We describe mechanisms for the allocation of a scarce resource among mul...
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...
read it
-
Untangling Dense Knots by Learning Task-Relevant Keypoints
Untangling ropes, wires, and cables is a challenging task for robots due...
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...
read it
-
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
Safety remains a central obstacle preventing widespread use of RL in the...
read it
-
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
Fully quantized training (FQT), which uses low-bitwidth hardware by quan...
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...
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...
read it
-
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Large-scale labeled training datasets have enabled deep neural networks ...
read it
-
Benchmarking Semi-supervised Federated Learning
Federated learning promises to use the computational power of edge devic...
read it
-
Optimizing Prediction Serving on Low-Latency Serverless Dataflow
Prediction serving systems are designed to provide large volumes of low-...
read it
-
Boundary thickness and robustness in learning models
Robustness of machine learning models to various adversarial and non-adv...
read it
-
Contrastive Code Representation Learning
Machine-aided programming tools such as automated type predictors and au...
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...
read it
-
Hindsight Logging for Model Training
Due to the long time-lapse between the triggering and detection of a bug...
read it
-
SegNBDT: Visual Decision Rules for Segmentation
The black-box nature of neural networks limits model decision interpreta...
read it
-
Ansor : Generating High-Performance Tensor Programs for Deep Learning
High-performance tensor programs are crucial to guarantee efficient exec...
read it
-
FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function
Neural Architecture Search (NAS) yields state-of-the-art neural networks...
read it
-
CoVista: A Unified View on Privacy Sensitive Mobile Contact Tracing Effort
Governments around the world have become increasingly frustrated with te...
read it
-
Thompson Sampling for Linearly Constrained Bandits
We address multi-armed bandits (MAB) where the objective is to maximize ...
read it
-
Mechanism Design with Bandit Feedback
We study a multi-round welfare-maximising mechanism design problem, wher...
read it
-
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Differentiable Neural Architecture Search (DNAS) has demonstrated great ...
read it
-
NBDT: Neural-Backed Decision Trees
Deep learning is being adopted in settings where accurate and justifiabl...
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...
read it
-
Frustratingly Simple Few-Shot Object Detection
Detecting rare objects from a few examples is an emerging problem. Prior...
read it
-
A Fault-Tolerance Shim for Serverless Computing
Serverless computing has grown in popularity in recent years, with an in...
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...
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...
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...
read it
-
SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis
Automatic speech synthesis is a challenging task that is becoming increa...
read it
-
Cloudburst: Stateful Functions-as-a-Service
Function-as-a-Service (FaaS) platforms and "serverless" cloud computing ...
read it
-
Towards Scalable Dataframe Systems
Dataframes are a popular and convenient abstraction to represent, struct...
read it
-
Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization
Modern neural networks are increasingly bottlenecked by the limited capa...
read it
-
Helen: Maliciously Secure Coopetitive Learning for Linear Models
Many organizations wish to collaboratively train machine learning models...
read it
-
On-Policy Robot Imitation Learning from a Converging Supervisor
Existing on-policy imitation learning algorithms, such as DAgger, assume...
read it
-
Task-Aware Deep Sampling for Feature Generation
The human ability to imagine the variety of appearances of novel objects...
read it
-
Extending Deep Model Predictive Control with Safety Augmented Value Estimation from Demonstrations
Reinforcement learning (RL) for robotics is challenging due to the diffi...
read it
-
ACE: Adapting to Changing Environments for Semantic Segmentation
Deep neural networks exhibit exceptional accuracy when they are trained ...
read it
-
TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
Learning good feature embeddings for images often requires substantial t...
read it
-
SysML: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
read it
-
A Fog Robotics Approach to Deep Robot Learning: Application to Object Recognition and Grasp Planning in Surface Decluttering
The growing demand of industrial, automotive and service robots presents...
read it
-
Constrained Thompson Sampling for Wireless Link Optimization
Wireless communication systems operate in complex time-varying environme...
read it
-
Cloud Programming Simplified: A Berkeley View on Serverless Computing
Serverless cloud computing handles virtually all the system administrati...
read it
-
The OoO VLIW JIT Compiler for GPU Inference
Current trends in Machine Learning (ML) inference on hardware accelerate...
read it
-
Serverless Computing: One Step Forward, Two Steps Back
Serverless computing offers the potential to program the cloud in an aut...
read it
-
InferLine: ML Inference Pipeline Composition Framework
The dominant cost in production machine learning workloads is not traini...
read it
-
Using Multitask Learning to Improve 12-Lead Electrocardiogram Classification
We develop a multi-task convolutional neural network (CNN) to classify m...
read it
-
Inter-BMV: Interpolation with Block Motion Vectors for Fast Semantic Segmentation on Video
Models optimized for accuracy on single images are often prohibitively s...
read it
-
Scaling Video Analytics Systems to Large Camera Deployments
New computer vision techniques, which enable accurate extraction of insi...
read it
-
Tune: A Research Platform for Distributed Model Selection and Training
Modern machine learning algorithms are increasingly computationally dema...
read it