@ChangDeng3 Profile picture

Chang Deng

@ChangDeng3

https://t.co/heTiTf2nR4

Joined May 2018
Similar User
Li Bo photo

@BoLi68567011

geeseathletics photo

@geeseathletics

lisamovius.bsky.social 🟧🌈 photo

@lisamovius

Maddie Ummel (2024) photo

@MaddieUmmel2024

Yunxin Li photo

@LyxTg

Mufeng Tang photo

@mufeng_tang

Hung-Ting Chen photo

@hungting_chen

Cong (Clarence) Jiang photo

@statsCong

Xiaokang Chen photo

@PKUCXK

Andre Niyongabo Rubungo photo

@andre_niyongabo

Haofei Yu photo

@haofeiyu44

Chad Koerner photo

@ChadKoerner

Adams photo

@hadamz_raj

MKCrowson photo

@mk_crowson

Jifan Zhang photo

@jifan_zhang

Chang Deng Reposted

Our new textbook Theoretical Foundations of Conformal Prediction is out! Conformal prediction is a a statistical technique that augments ML systems with uncertainty information for safe deployment. This book lays out the core theory. arxiv.org/abs/2411.11824


Chang Deng Reposted

Breaking the curse of dimensionality in structured density estimation ift.tt/YdgxGh6


Chang Deng Reposted

Likelihood-based Differentiable Structure Learning ift.tt/QxbNpv0


Chang Deng Reposted

Hmm how does one get valid post-selection inference for causal effects after causal discovery?? Good question! We have a new paper about this you might enjoy: arxiv.org/abs/2405.06763 And if you're at ACIC check out my student's Ting-Hsuan Chang’s poster about it!


Chang Deng Reposted

Announcing 𝐕𝐨𝐢𝐜𝐞𝐂𝐫𝐚𝐟𝐭🪄 SotA for both speech editing and zero-shot text-to-speech, Outperforming VALL-E, XTTS-v2, etc. VoiceCraft works on in-the-wild data such as movies, random videos and podcasts We fully open source it at tinyurl.com/3r8fvyzk


Chang Deng Reposted

👏 🎉 Congratulations to Veronika Rockova (@UChicago), winner of the 2024 COPSS Presidents' Award! The Presidents' Award is given annually to a young member of the statistical community in recognition of outstanding contributions to the profession of statistics.

Tweet Image 1

Chang Deng Reposted

Applying statistical learning theory to deep learning. (arXiv:2311.15404v1 [cs.LG]) ift.tt/58MeHgo


Chang Deng Reposted

I've been using a GPT4 paper assistant that reads the daily ArXiv feed and makes personalized recommendations in Slack. It's worked pretty well for me (today's paper demo tatsu-lab.github.io/gpt_paper_assi…). If this sounds helpful, you can set up your own bot here github.com/tatsu-lab/gpt_….

Tweet Image 1
Tweet Image 2

Chang Deng Reposted

Generalizing Nonlinear ICA Beyond Structural Sparsity. (arXiv:2311.00866v1 [cs.LG]) ift.tt/mty1IQJ


Chang Deng Reposted

Mathematical Introduction to Deep Learning: Methods, Implementations, and Theory. (arXiv:2310.20360v1 [cs.LG]) ift.tt/RbCXIaL


Chang Deng Reposted

ChatGPT can now browse the internet to provide you with current and authoritative information, complete with direct links to sources. It is no longer limited to data before September 2021.


Chang Deng Reposted

Lecture notes from summer schools in Princeton (2021) and Les Houches (2022), with Theodor Misiakiewicz: arxiv.org/abs/2308.13431


Chang Deng Reposted

👏 The secret is out! The recipient of the 2023 COPSS President’s Award is… Dr. Ryan Tibshirani from @UCBerkeley !! #JSM2023

Tweet Image 1

Chang Deng Reposted

Causal-learn: Causal Discovery in Python. (arXiv:2307.16405v1 [cs.LG]) ift.tt/hIBQgo2


Chang Deng Reposted

I've proven the strangest result of my career.. The classic idea that gradient descent's rate is best with constant stepsizes 1/L is wrong. The idea that we need stepsizes in (0,2/L) for convergence is wrong. Periodic long steps are better, provably. arxiv.org/abs/2307.06324

Tweet Image 1

Chang Deng Reposted

new book on ML theory by Tong Zhang??? sign me right up!!! cambridge.org/core/books/mat…


Chang Deng Reposted

Ever wanted to understand the convergence theory of SGD? Probably best to start with this new paper (arxiv.org/abs/2301.11235) that collects all simple proofs in one place: momentum, minibatching, prox, averaging, and more. Covers nonconvex and nonsmooth cases too.


Chang Deng Reposted

Can’t go to a parade Can’t go to school Can’t go to a supermarket Can’t go to pray Can’t go to the movies Can’t go to a concert Can’t go to a nightclub Can’t go to a restaurant Can’t go to a park Can’t go to a mall There’s nowhere you can go in America to avoid gun violence


Chang Deng Reposted

We often prefer collaborating with people we know or those of high status. That makes it very difficult for hardworking and motivated junior researchers to get enough support to flourish. Is it possible to reduce this barrier? I'v been running some experiments to find out! 1/6


Chang Deng Reposted

I am delighted to announce that my new book, “Probabilistic Machine Learning: An Introduction”, is finally available in print format! You can order it from mitpress.mit.edu/books/probabil…, or from Amazon. Also available at probml.ai 1/4

Tweet Image 1

Loading...

Something went wrong.


Something went wrong.