Assistant Professor @PurdueECE | Postdoc @MIT_CSAIL | PhD @UChicagoCS
Joined July 2013
- Tweets 110
- Following 580
- Followers 337
- Likes 449
6 Photos and videos
Pinned Tweet
1 Jun 2024
Save the Date for an #NSF DESC Workshop on Sustainable Computing on Aug 20-21, 2024. This workshop will focus on the dimensions of #AI, water, and biodiversity dimensions, extending beyond just carbon footprints. #SustainableComputing
1
2
496
16 Nov 2023
I am recruiting PhD students at Purdue ECE (not CS) starting from Fall 2024!
We have ongoing projects in:
- Observational Studies and Causal Inference for Distributed Systems.
- Sustainable Cloud Datacenters
Students with background in sys, arch, ML are welcome to apply!
1
20
61
7,354
17 Nov 2023
Application link: engineering.purdue.edu/ECE/A…
Deadline: December 1, 2023
#phdopportunity #systemsresearch #comparchresearch #mlsys
1
473
#NITRD30th has posters presented by @NSF & @compcomcon's Computing Innovation Fellows! Take a look @ CIFellows' cutting-edge research on emerging #NIT technology. What a great career-enhancing bridge experience NSF & Computing Community Consortium provide nitrd.gov/30th-anniversary-o…
3
1
25 May 2022
1
9
Yi Ding retweeted
20 Oct 2021
🚨New paper🚨 at Onward! “Programming with Neural Surrogates of Programs” with @counterfac and @mcarbin
We show why and how you should replace all your programs with neural networks.
alexrenda.com/onward-2021 youtube.com/watch?v=rM8SwKOB… 🧵1/13
3
20
100
Yi Ding retweeted
20 Oct 2021
The neuro-symbolic learning/programming space is quite varied in its ideas. But, this is neat work with the team cleaving out a survey and demonstration of a narrower set of work on replacing programs with neural networks, along with what you get (and don't!) when you so do.
20 Oct 2021
🚨New paper🚨 at Onward! “Programming with Neural Surrogates of Programs” with @counterfac and @mcarbin
We show why and how you should replace all your programs with neural networks.
alexrenda.com/onward-2021 youtube.com/watch?v=rM8SwKOB… 🧵1/13
2
16
24 Aug 2021
How to incorporate prior knowledge and understand how fast software configurations are arrived?
Our paper: Generalizable and Interpretable Learning for Configuration Extrapolation (w/ A. Pervaiz, H. Hoffmann, @mcarbin) published in #esecfse21 @FSEconf, has a few ideas!
1
6
22
24 Aug 2021
Paper: y-ding.github.io/papers/FSE2…
We introduce a new configuration extrapolation tool, GIL . GIL builds a hierarchical performance model by adding a low-level system metrics layer between SW configurations and final performance.
1
2
24 Aug 2021
With the extra layer, GIL produces interpretable results to help users understand the underlying SW/HW factors that cause the low performance, and gain insights into how faster configurations are achieved.
2
27 Apr 2021
Excited to see this work out. Great collaboration on applying causal DAG analysis as the quantitative tool to support findings on the relationships between park visits and crimes. 👇
27 Apr 2021
Excited to announce our new paper: Neighborhood street activity and greenspace usage uniquely contribute to predicting crime with @jamessaxon @BettencourtLuis @kharloews @counterfac Hank Hoffman @EnvNeuroLab Marc Berman.
@Nature_NPJ Urban Sustainability: nature.com/articles/s42949-0…
3
29 Mar 2021
I updated my list of causal system papers in #PL #SE column. Thank @jimmykoppel for suggesting these amazing papers! It seems PLSE is ahead of other CS fields in incorporating causality. Dependence is the key.
github.com/y-ding/causal-sys…
28 Jan 2021
Tired of ML for Systems? It's time to rethink and get a perspective on causal inference for systems. I assembled a paper list on Causal Systems, covering areas of #architecture, #database, #networking, #OS, #SE, and #PL: 👇
github.com/y-ding/causal-sys…
1
4
18 Mar 2021
Thanks CRA @CRAtweets to feature my CIFellow project on Improving System Efficiency and Reliability with Causal Learning! Check it out👇
1
10
18 Mar 2021
Thank CCC @compcomcon for featuring my project on Improving System Efficiency and Reliability with Causal Learning! Check it out👇
1
1
4
1 Mar 2021
Interested in robust ML models other than robust neural networks? Check out robust ensemble tree 👇
28 Feb 2021
Using Twitter spam detection as an example, I wrote about how to train robust trees for security (USENIX Sec 21). Our most exciting result is, we can increase the feature manipulation cost for adaptive attackers to evade the robust tree ensemble by 10.6X.
surrealyz.medium.com/robust-…
1
8
28 Jan 2021
Tired of ML for Systems? It's time to rethink and get a perspective on causal inference for systems. I assembled a paper list on Causal Systems, covering areas of #architecture, #database, #networking, #OS, #SE, and #PL: 👇
github.com/y-ding/causal-sys…
5
8
26
28 Jan 2021
It is inspired by System Configuration Management list from @tianyin_xu
x.com/tianyin_xu/status/1338…
14 Dec 2020
I assembled a list of papers and articles on configuration management for cloud/systems:
github.com/tianyin/configura…
Hope it helps.
1
1
11 Jan 2021
In ML for systems problems #MLSys, is higher prediction accuracy equivalent to the better system outcome? The answer is NO! I wrote a blog post explaining why 👇:
link.medium.com/7l1gRg5BTcb
1
1
7
11 Dec 2020
I start an academic blog today and here is my first post: How to write good systems papers? Most of the tips come from my PhD advisor Hank Hoffmann.
Retweets are appreciated.
counterfac.medium.com/how-to…
1
18
63