127 citations · 367 across the 12 of their papers we have counts for
12 papers
Skyplane: Optimizing Transfer Cost and Throughput Using Cloud-Aware Overlays
Paras Jain, Sam Kumar, Sarah Wooders +3
Cloud applications are increasingly distributing data across multiple regions and cloud providers. Unfortunately, wide-area bulk data transfers are often slow, bottlenecking applic…
POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging
Shishir G. Patil, Paras Jain, Prabal Dutta +2
Fine-tuning models on edge devices like mobile phones would enable privacy-preserving personalization over sensitive data. However, edge training has historically been limited to r…
Representing Long-Range Context for Graph Neural Networks with Global Attention
Zhanghao Wu, Paras Jain, Matthew A. Wright +3
Graph neural networks are powerful architectures for structured datasets. However, current methods struggle to represent long-range dependencies. Scaling the depth or width of GNNs…
Grounded Graph Decoding Improves Compositional Generalization in Question Answering
Yu Gai, Paras Jain, Wendi Zhang +3
Question answering models struggle to generalize to novel compositions of training patterns, such to longer sequences or more complex test structures. Current end-to-end models lea…
Accelerating Quadratic Optimization with Reinforcement Learning
Jeffrey Ichnowski, Paras Jain, Bartolomeo Stellato +6
First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapid…
Contrastive Code Representation Learning
Paras Jain, Ajay Jain, Tianjun Zhang +3
Recent work learns contextual representations of source code by reconstructing tokens from their context. For downstream semantic understanding tasks like summarizing code in Engli…
Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization
Paras Jain, Ajay Jain, Aniruddha Nrusimha +5
We formalize the problem of trading-off DNN training time and memory requirements as the tensor rematerialization optimization problem, a generalization of prior checkpointing stra…
Revec: Program Rejuvenation through Revectorization
Charith Mendis, Ajay Jain, Paras Jain +1
Modern microprocessors are equipped with Single Instruction Multiple Data (SIMD) or vector instructions which expose data level parallelism at a fine granularity. Programmers explo…
The OoO VLIW JIT Compiler for GPU Inference
Paras Jain, Xiangxi Mo, Ajay Jain +3
Current trends in Machine Learning~(ML) inference on hardware accelerated devices (e.g., GPUs, TPUs) point to alarmingly low utilization. As ML inference is increasingly time-bound…
Dynamic Space-Time Scheduling for GPU Inference
Paras Jain, Xiangxi Mo, Ajay Jain +5
Serving deep neural networks in latency critical interactive settings often requires GPU acceleration. However, the small batch sizes typical in online inference results in poor GP…
Scalable Architecture for Anomaly Detection and Visualization in Power Generating Assets
Paras Jain, Chirag Tailor, Sam Ford +5
Power-generating assets (e.g., jet engines, gas turbines) are often instrumented with tens to hundreds of sensors for monitoring physical and performance degradation. Anomaly detec…
Spotting Suspicious Reviews via (Quasi-)clique Extraction
Paras Jain, Shang-Tse Chen, Mozhgan Azimpourkivi +2
How to tell if a review is real or fake? What does the underworld of fraudulent reviewing look like? Detecting suspicious reviews has become a major issue for many online services.…