Search Results for author: Mohammad Alizadeh

Found 32 papers, 12 papers with code

Reparo: Loss-Resilient Generative Codec for Video Conferencing

no code implementations23 May 2023 Tianhong Li, Vibhaalakshmi Sivaraman, Lijie Fan, Mohammad Alizadeh, Dina Katabi

Our experiments on publicly available video conferencing datasets show that Reparo outperforms state-of-the-art FEC-based video conferencing in terms of both video quality (measured by PSNR) and video freezes.

Counterfactual Identifiability of Bijective Causal Models

1 code implementation4 Feb 2023 Arash Nasr-Esfahany, Mohammad Alizadeh, Devavrat Shah

We study counterfactual identifiability in causal models with bijective generation mechanisms (BGM), a class that generalizes several widely-used causal models in the literature.

Locally Constrained Policy Optimization for Online Reinforcement Learning in Non-Stationary Input-Driven Environments

no code implementations4 Feb 2023 Pouya Hamadanian, Arash Nasr-Esfahany, Siddartha Sen, Malte Schwarzkopf, Mohammad Alizadeh

We study online Reinforcement Learning (RL) in non-stationary input-driven environments, where a time-varying exogenous input process affects the environment dynamics.

Reinforcement Learning (RL)

FactorJoin: A New Cardinality Estimation Framework for Join Queries

no code implementations11 Dec 2022 Ziniu Wu, Parimarjan Negi, Mohammad Alizadeh, Tim Kraska, Samuel Madden

Neither classical nor learning-based methods yield satisfactory performance when estimating the cardinality of the join queries.

Gemino: Practical and Robust Neural Compression for Video Conferencing

no code implementations21 Sep 2022 Vibhaalakshmi Sivaraman, Pantea Karimi, Vedantha Venkatapathy, Mehrdad Khani, Sadjad Fouladi, Mohammad Alizadeh, Frédo Durand, Vivienne Sze

We design Gemino, a new neural compression system for video conferencing based on a novel high-frequency-conditional super-resolution pipeline.


Demystifying Reinforcement Learning in Time-Varying Systems

no code implementations14 Jan 2022 Pouya Hamadanian, Malte Schwarzkopf, Siddartha Sen, Mohammad Alizadeh

Such agents must explore and learn new environments, without hurting the system's performance, and remember them over time.

reinforcement-learning Reinforcement Learning (RL)

CausalSim: A Causal Framework for Unbiased Trace-Driven Simulation

1 code implementation5 Jan 2022 Abdullah Alomar, Pouya Hamadanian, Arash Nasr-Esfahany, Anish Agarwal, Mohammad Alizadeh, Devavrat Shah

Key to CausalSim is mapping unbiased trace-driven simulation to a tensor completion problem with extremely sparse observations.

Causal Inference

Efficient Strong Scaling Through Burst Parallel Training

no code implementations19 Dec 2021 Seo Jin Park, Joshua Fried, Sunghyun Kim, Mohammad Alizadeh, Adam Belay

As emerging deep neural network (DNN) models continue to grow in size, using large GPU clusters to train DNNs is becoming an essential requirement to achieving acceptable training times.

Updating Street Maps using Changes Detected in Satellite Imagery

no code implementations13 Oct 2021 Favyen Bastani, Songtao He, Satvat Jagwani, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Sam Madden, Mohammad Amin Sadeghi

To address this challenge, much work has studied automatically processing geospatial data sources such as GPS trajectories and satellite images to reduce the cost of maintaining digital maps.

Efficient Video Compression via Content-Adaptive Super-Resolution

1 code implementation ICCV 2021 Mehrdad Khani, Vibhaalakshmi Sivaraman, Mohammad Alizadeh

SRVC decodes the video by passing the decompressed low-resolution video frames through the (time-varying) super-resolution model to reconstruct high-resolution video frames.

Super-Resolution Video Compression

Cortex: Harnessing Correlations to Boost Query Performance

no code implementations12 Dec 2020 Vikram Nathan, Jialin Ding, Tim Kraska, Mohammad Alizadeh

Unlike prior work, Cortex can adapt itself to any existing primary index, whether single or multi-dimensional, to harness a broad variety of correlations, such as those that exist between more than two attributes or have a large number of outliers.

Neural Large Neighborhood Search

no code implementations NeurIPS Workshop LMCA 2020 Ravichandra Addanki, Vinod Nair, Mohammad Alizadeh

Results on several datasets show that it is possible to learn a neighbor selection policy that allows LNS to efficiently find good solutions.

Combinatorial Optimization

Tsunami: A Learned Multi-dimensional Index for Correlated Data and Skewed Workloads

no code implementations23 Jun 2020 Jialin Ding, Vikram Nathan, Mohammad Alizadeh, Tim Kraska

Filtering data based on predicates is one of the most fundamental operations for any modern data warehouse.

Real-Time Video Inference on Edge Devices via Adaptive Model Streaming

1 code implementation ICCV 2021 Mehrdad Khani, Pouya Hamadanian, Arash Nasr-Esfahany, Mohammad Alizadeh

Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks.

Knowledge Distillation Semantic Segmentation +2

RoadTagger: Robust Road Attribute Inference with Graph Neural Networks

1 code implementation28 Dec 2019 Songtao He, Favyen Bastani, Satvat Jagwani, Edward Park, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Samuel Madden, Mohammad Amin Sadeghi

The usage of graph neural networks allows information propagation on the road network graph and eliminates the receptive field limitation of image classifiers.

Learning Multi-dimensional Indexes

no code implementations3 Dec 2019 Vikram Nathan, Jialin Ding, Mohammad Alizadeh, Tim Kraska

Scanning and filtering over multi-dimensional tables are key operations in modern analytical database engines.

Inferring and Improving Street Maps with Data-Driven Automation

no code implementations2 Oct 2019 Favyen Bastani, Songtao He, Satvat Jagwani, Edward Park, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Sam Madden, Mohammad Amin Sadeghi

Through an evaluation on a large-scale dataset including satellite imagery, GPS trajectories, and ground-truth map data in forty cities, we show that Mapster makes automation practical for map editing, and enables the curation of map datasets that are more complete and up-to-date at less cost.

Practical Low Latency Proof of Work Consensus

2 code implementations25 Sep 2019 Lei Yang, Vivek Bagaria, Gerui Wang, Mohammad Alizadeh, David Tse, Giulia Fanti, Pramod Viswanath

Bitcoin is the first fully-decentralized permissionless blockchain protocol to achieve a high level of security, but at the expense of poor throughput and latency.

Distributed, Parallel, and Cluster Computing Cryptography and Security Networking and Internet Architecture

Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning

3 code implementations20 Jun 2019 Ravichandra Addanki, Shaileshh Bojja Venkatakrishnan, Shreyan Gupta, Hongzi Mao, Mohammad Alizadeh

Unlike prior approaches that only find a device placement for a specific computation graph, Placeto can learn generalizable device placement policies that can be applied to any graph.

BIG-bench Machine Learning Reinforcement Learning (RL)

Machine-Assisted Map Editing

no code implementations17 Jun 2019 Favyen Bastani, Songtao He, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Sam Madden

Systems to automatically infer road network graphs from aerial imagery and GPS trajectories have been proposed to improve coverage of road maps.

graph construction

Adaptive Neural Signal Detection for Massive MIMO

1 code implementation11 Jun 2019 Mehrdad Khani, Mohammad Alizadeh, Jakob Hoydis, Phil Fleming

We propose MMNet, a deep learning MIMO detection scheme that significantly outperforms existing approaches on realistic channels with the same or lower computational complexity.

Understanding & Generalizing AlphaGo Zero

no code implementations ICLR 2019 Ravichandra Addanki, Mohammad Alizadeh, Shaileshh Bojja Venkatakrishnan, Devavrat Shah, Qiaomin Xie, Zhi Xu

AlphaGo Zero (AGZ) introduced a new {\em tabula rasa} reinforcement learning algorithm that has achieved superhuman performance in the games of Go, Chess, and Shogi with no prior knowledge other than the rules of the game.

Decision Making reinforcement-learning +2

Restructuring Endpoint Congestion Control

1 code implementation SIGCOMM '18 2018 Akshay Narayan, Frank Cangialosi, Deepti Raghavan, Prateesh Goyal Srinivas Narayana, Radhika Mittal, Mohammad Alizadeh, Hari Balakrishnan

Each datapath—such as the Linux kernel TCP, UDP-based QUIC, or kernel-bypass transports like mTCP-on-DPDK—summarizes information about packet round-trip times, receptions, losses, and ECN via a well-defined interface to algorithms running in the off-datapath Congestion Control Plane (CCP).

Variance Reduction for Reinforcement Learning in Input-Driven Environments

no code implementations ICLR 2019 Hongzi Mao, Shaileshh Bojja Venkatakrishnan, Malte Schwarzkopf, Mohammad Alizadeh

We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system.

Meta-Learning Object Tracking +3

Cannot find the paper you are looking for? You can Submit a new open access paper.