activity
20122023
most citedTensorIR: An Abstraction for Automatic Tensorized Program Optimization

3 citations · 5 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2023

Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling

Tianqi Chen, Mingyuan Zhou

Learning to denoise has emerged as a prominent paradigm to design state-of-the-art deep generative models for natural images. How to use it to model the distributions of both conti…

stat.AP20232 cited

Bayesian subtyping for multi-state brain functional connectome with application on adolescent brain cognition

Tianqi Chen, Chichun Tan, Hongyu Zhao +3

Converging evidence indicates that the heterogeneity of cognitive profiles may arise through detectable alternations in brain functions. Particularly, brain functional connectivity…

cs.LG2023

ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines

Siyuan Chen, Pratik Fegade, Tianqi Chen +2

Batching has a fundamental influence on the efficiency of deep neural network (DNN) execution. However, for dynamic DNNs, efficient batching is particularly challenging as the data…

cs.LG20223 cited

TensorIR: An Abstraction for Automatic Tensorized Program Optimization

Siyuan Feng, Bohan Hou, Hongyi Jin +8

Deploying deep learning models on various devices has become an important topic. The wave of hardware specialization brings a diverse set of acceleration primitives for multi-dimen…

cs.LG2014

A Parallel and Efficient Algorithm for Learning to Match

Jingbo Shang, Tianqi Chen, Hang Li +2

Many tasks in data mining and related fields can be formalized as matching between objects in two heterogeneous domains, including collaborative filtering, link prediction, image t…

math-ph2012

Flow Decomposition Reveals Dynamical Structure of Markov Process

Jianghong Shi, Tianqi Chen, Bo Yuan +1

Markov process is widely applied in almost all aspects of literature, especially important for understanding non-equilibrium processes. We introduce a decomposition to general Mark…