b'Ion Stoica'

research

∙ 08/06/2023

Leveraging Cloud Computing to Make Autonomous Vehicles Safer

The safety of autonomous vehicles (AVs) depends on their ability to perf...

0 Peter Schafhalter, et al. ∙

research

∙ 03/13/2023

FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

The high computational and memory requirements of large language model (...

0 Ying Sheng, et al. ∙

research

∙ 02/11/2023

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Recent advances in instruction-following large language models (LLMs) ha...

0 Daniel Kang, et al. ∙

research

∙ 01/10/2023

Exoshuffle-CloudSort

We present Exoshuffle-CloudSort, a sorting application running on top of...

0 Frank Sifei Luan, et al. ∙

research

∙ 11/09/2022

ZK-IMG: Attested Images via Zero-Knowledge Proofs to Fight Disinformation

Over the past few years, AI methods of generating images have been incre...

0 Daniel Kang, et al. ∙

research

∙ 10/19/2022

CLUTR: Curriculum Learning via Unsupervised Task Representation Learning

Reinforcement Learning (RL) algorithms are often known for sample ineffi...

0 Abdus Salam Azad, et al. ∙

research

∙ 10/17/2022

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs

As ML models have increased in capabilities and accuracy, so has the com...

0 Daniel Kang, et al. ∙

research

∙ 10/13/2022

Skyplane: Optimizing Transfer Cost and Throughput Using Cloud-Aware Overlays

Cloud applications are increasingly distributing data across multiple re...

0 Paras Jain, et al. ∙

research

∙ 08/16/2022

Context-Aware Streaming Perception in Dynamic Environments

Efficient vision works maximize accuracy under a latency budget. These w...

7 Gur-Eyal Sela, et al. ∙

research

∙ 07/15/2022

POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging

Fine-tuning models on edge devices like mobile phones would enable priva...

10 Shishir G. Patil, et al. ∙

research

∙ 06/28/2022

NumS: Scalable Array Programming for the Cloud

Scientists increasingly rely on Python tools to perform scalable distrib...

10 Melih Elibol, et al. ∙

research

∙ 05/19/2022

FogROS 2: An Adaptive and Extensible Platform for Cloud and Fog Robotics Using ROS 2

Mobility, power, and price points often dictate that robots do not have ...

0 Jeffrey Ichnowski, et al. ∙

research

∙ 05/14/2022

The Sky Above The Clouds

Technology ecosystems often undergo significant transformations as they ...

0 Sarah Chasins, et al. ∙

research

∙ 03/09/2022

Exoshuffle: Large-Scale Shuffle at the Application Level

Shuffle is a key primitive in large-scale data processing applications. ...

0 Frank Sifei Luan, et al. ∙

research

∙ 01/21/2022

Representing Long-Range Context for Graph Neural Networks with Global Attention

Graph neural networks are powerful architectures for structured datasets...

2 Zhanghao Wu, et al. ∙

research

∙ 01/05/2022

Balsa: Learning a Query Optimizer Without Expert Demonstrations

Query optimizers are a performance-critical component in every database ...

13 Zongheng Yang, et al. ∙

research

∙ 12/07/2021

MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance

Safe exploration is critical for using reinforcement learning (RL) in ri...

19 Michael Luo, et al. ∙

research

∙ 11/05/2021

Grounded Graph Decoding Improves Compositional Generalization in Question Answering

Question answering models struggle to generalize to novel compositions o...

16 Yu Gai, et al. ∙

research

∙ 07/22/2021

Accelerating Quadratic Optimization with Reinforcement Learning

First-order methods for quadratic optimization such as OSQP are widely u...

10 Jeffrey Ichnowski, et al. ∙

research

∙ 06/18/2021

Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments

The capability of reinforcement learning (RL) agent directly depends on ...

21 Abdus Salam Azad, et al. ∙

research

∙ 06/11/2021

Online Learning of Competitive Equilibria in Exchange Economies

The sharing of scarce resources among multiple rational agents is one of...

2 Wenshuo Guo, et al. ∙

research

∙ 06/06/2021

PAC Best Arm Identification Under a Deadline

We study (ϵ, δ)-PAC best arm identification, where a decision-maker must...

2 Brijen Thananjeyan, et al. ∙

research

∙ 04/29/2021

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

The increasing size of neural network models has been critical for impro...

13 Jianfei Chen, et al. ∙

research

∙ 04/16/2021

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

We present Pylot, a platform for autonomous vehicle (AV) research and de...

0 Ionel Gog, et al. ∙

research

∙ 04/08/2021

Read-Write Quorum Systems Made Practical

Quorum systems are a powerful mechanism for ensuring the consistency of ...

0 Michael Whittaker, et al. ∙

research

∙ 12/31/2020

Scaling Replicated State Machines with Compartmentalization [Technical Report]

State machine replication protocols, like MultiPaxos and Raft, are a cri...

0 Michael Whittaker, et al. ∙

research

∙ 12/19/2020

Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers

Video analytics applications use edge compute servers for the analytics ...

12 Romil Bhardwaj, et al. ∙

research

∙ 12/15/2020

Online Learning Demands in Max-min Fairness

We describe mechanisms for the allocation of a scarce resource among mul...

5 Kirthevasan Kandasamy, et al. ∙

research

∙ 11/25/2020

Distributed Reinforcement Learning is a Dataflow Problem

Researchers and practitioners in the field of reinforcement learning (RL...

20 Eric Liang, et al. ∙

research

∙ 10/31/2020

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...

11 Brijen Thananjeyan, et al. ∙

research

∙ 10/12/2020

RackSched: A Microsecond-Scale Scheduler for Rack-Scale Computers (Technical Report)

Low-latency online services have strict Service Level Objectives (SLOs) ...

0 Hang Zhu, et al. ∙

research

∙ 07/18/2020

Matchmaker Paxos: A Reconfigurable Consensus Protocol [Technical Report]

State machine replication protocols, like MultiPaxos and Raft, are at th...

0 Michael Whittaker, et al. ∙

research

∙ 07/15/2020

FetchSGD: Communication-Efficient Federated Learning with Sketching

Existing approaches to federated learning suffer from a communication bo...

0 Daniel Rothchild, et al. ∙

research

∙ 07/10/2020

Variable Skipping for Autoregressive Range Density Estimation

Deep autoregressive models compute point likelihood estimates of individ...

2 Eric Liang, et al. ∙

research

∙ 07/09/2020

Contrastive Code Representation Learning

Machine-aided programming tools such as automated type predictors and au...

5 Paras Jain, et al. ∙

research

∙ 06/15/2020

NeuroCard: One Cardinality Estimator for All Tables

Query optimizers rely on accurate cardinality estimates to produce good ...

0 Zongheng Yang, et al. ∙

research

∙ 06/11/2020

Ansor : Generating High-Performance Tensor Programs for Deep Learning

High-performance tensor programs are crucial to guarantee efficient exec...

10 Lianmin Zheng, et al. ∙

research

∙ 05/27/2020

ProTuner: Tuning Programs with Monte Carlo Tree Search

We explore applying the Monte Carlo Tree Search (MCTS) algorithm in a no...

48 Ameer Haj-Ali, et al. ∙

research

∙ 04/19/2020

Mechanism Design with Bandit Feedback

We study a multi-round welfare-maximising mechanism design problem, wher...

4 Kirthevasan Kandasamy, et al. ∙

research

∙ 03/02/2020

AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learning

The performance of the code a compiler generates depends on the order in...

0 Qijing Huang, et al. ∙

research

∙ 02/29/2020

Bipartisan Paxos: A Modular State Machine Replication Protocol

There is no shortage of state machine replication protocols. From Genera...

0 Michael Whittaker, et al. ∙

research

∙ 02/13/2020

Hoplite: Efficient Collective Communication for Task-Based Distributed Systems

Collective communication systems such as MPI offer high performance grou...

0 Siyuan Zhuang, et al. ∙

research

∙ 01/08/2020

HyperSched: Dynamic Resource Reallocation for Model Development on a Deadline

Prior research in resource scheduling for machine learning training work...

0 Richard Liaw, et al. ∙

research

∙ 12/29/2019

Hierarchical Variational Imitation Learning of Control Programs

Autonomous agents can learn by imitating teacher demonstrations of the i...

17 Roy Fox, et al. ∙

research

∙ 11/30/2019

IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks

The practical usage of reinforcement learning agents is often bottleneck...

5 Michael Luo, et al. ∙

research

∙ 11/22/2019

Gemmini: An Agile Systolic Array Generator Enabling Systematic Evaluations of Deep-Learning Architectures

Advances in deep learning and neural networks have resulted in the rapid...

0 Hasan Genc, et al. ∙

research

∙ 10/11/2019

Blink: Fast and Generic Collectives for Distributed ML

Model parameter synchronization across GPUs introduces high overheads fo...

0 Guanhua Wang, et al. ∙

research

∙ 10/07/2019

Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization

Modern neural networks are increasingly bottlenecked by the limited capa...

12 Paras Jain, et al. ∙

research

∙ 09/20/2019

NeuroVectorizer: End-to-End Vectorization with Deep Reinforcement Learning

One of the key challenges arising when compilers vectorize loops for tod...

0 Ameer Haj-Ali, et al. ∙

research

∙ 08/04/2019

Deep Reinforcement Learning in System Optimization

The recent advancements in deep reinforcement learning have opened new h...

6 Ameer Haj-Ali, et al. ∙

Ion Stoica

Featured Co-authors