This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

Workshop: Machine Learning for Systems

Anna Goldie, Azalia Mirhoseini, Jonathan Raiman, Martin Maas, Xinlei XU

Sat, Dec 12th @ 17:00 GMT – Sun, Dec 13th @ 01:50 GMT
Abstract: **NeurIPS 2020 Workshop on Machine Learning for Systems**

Website: http://mlforsystems.org/

Submission Link: https://cmt3.research.microsoft.com/MLFS2020/Submission/Index

Important Dates:

Submission Deadline: **October 9th, 2020** (AoE)
Acceptance Notifications: October 23rd, 2020
Camera-Ready Submission: November 29th, 2020
Workshop: December 12th, 2020

Call for Papers:

Machine Learning for Systems is an interdisciplinary workshop that brings together researchers in computer systems and machine learning. This workshop is meant to serve as a platform to promote discussions between researchers in these target areas.

We invite submission of up to 4-page extended abstracts in the broad area of using machine learning in the design of computer systems. We are especially interested in submissions that move beyond using machine learning to replace numerical heuristics. This year, we hope to see novel system designs, streamlined cross-platform optimization, and new benchmarks for ML for Systems.

Accepted papers will be made available on the workshop website, but there will be no formal proceedings. Authors may therefore publish their work in other journals or conferences. The workshop will include invited talks from industry and academia as well as oral and poster presentations by workshop participants.

Areas of interest:

* Supervised, unsupervised, and reinforcement learning research with applications to:
- Systems Software
- Runtime Systems
- Distributed Systems
- Security
- Compilers, data structures, and code optimization
- Databases
- Computer architecture, microarchitecture, and accelerators
- Circuit design and layout
- Interconnects and Networking
- Storage
- Datacenters
* Representation learning for hardware and software
* Optimization of computer systems and software
* Systems modeling and simulation
* Implementations of ML for Systems and challenges
* High quality datasets for ML for Systems problems

Submission Instructions:

We welcome submissions of up to 4 pages (not including references). This is not a strict limit, but authors are encouraged to adhere to it if possible. All submissions must be in PDF format and should follow the NeurIPS 2020 format. Submissions do not have to be anonymized.

Please submit your paper no later than October 9th, 2020 midnight anywhere in the world to CMT (Link available soon).

Chat

To ask questions please use rocketchat, available only upon registration and login.

Schedule

17:00 – 17:15 GMT
Opening Remarks
17:15 – 17:50 GMT
Invited Speaker: Christina Delimitrou
Christina Delimitrou
17:50 – 18:25 GMT
Invited Speaker: Ed Chi
Ed Chi
18:25 – 18:40 GMT
Break
18:40 – 18:50 GMT
Program Graphs for Machine Learning
Chris Cummins
18:50 – 19:00 GMT
DEff-ARTS: Differentiable Efficient Architecture Search
Sulaiman Sadiq
19:00 – 19:10 GMT
Learning Local Advantage Functions for Generalizable Graph Optimizations
Yifan Wu
19:10 – 19:20 GMT
A Deep Learning Based Cost Model for Automatic Code Optimization
Riyadh Baghdadi
19:20 – 19:30 GMT
Q&A (Talks #1-4)
19:30 – 20:05 GMT
Invited Speaker: Bryan Catanzaro
Bryan Catanzaro
20:05 – 21:00 GMT
Break
21:00 – 21:10 GMT
NVCell: Generate Standard Cell Layout in Advanced Technology Nodes with Reinforcement Learning
Mark Ren
21:10 – 21:20 GMT
A General Framework For VLSI Tool Parameter Optimization with Deep Reinforcement Learning
Anthony Agnesina
21:20 – 21:30 GMT
Learned Hardware/Software Co-Design of Neural Accelerators
Zhan Shi
21:30 – 21:40 GMT
Apollo: Transferable Architecture Exploration
Amir Yazdanbakhsh
21:40 – 21:50 GMT
Q&A (Talks #5-8)
21:50 – 22:25 GMT
Invited Speaker: Benoit Steiner
Benoit Steiner
22:25 – 22:35 GMT
Learned Indexes for a Google-scale Disk-based Database
Deniz Altınbüken
22:35 – 22:45 GMT
Matrix Profile Index Prediction for Streaming Time Series
Maryam Shahcheraghi
22:45 – 22:55 GMT
Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
Somdeb Majumdar
22:55 – 23:05 GMT
MicroPlace: Placing Micro Virtual Machines with Hindsight Imitation
Bharathan Balaji
23:05 – 23:15 GMT
Q&A (Talks #9-12)
23:15 – 23:30 GMT
Break
Sat, Dec 12th @ 23:30 GMT – Sun, Dec 13th @ 00:05 GMT
Invited Speaker: Justin Gottschlich
Justin Gottschlich
00:05 – 00:15 GMT
Resonance: Replacing Software Constants with Context-Aware Models in Real-time Communication
Jayant Gupchup
00:15 – 00:25 GMT
CADET: A Systematic Method For Debugging Misconfigurations using Counterfactual Reasoning
Shahriar Iqbal
00:25 – 00:35 GMT
The Law of Attraction: Affinity-Aware Placement Optimization using Graph Neural Networks
Yi-Chen Lu
00:35 – 00:45 GMT
Highly Available Data Parallel ML training on Mesh Networks
Sameer Kumar
00:45 – 00:55 GMT
ControlFlag: A Self-supervised Idiosyncratic Pattern Detection System for Software Control Structures
Niranjan Hasabnis
00:55 – 01:05 GMT
Q&A (Talks #13-17)
01:05 – 01:40 GMT
Invited Speaker: Kunle Olukotun
Kunle Olukotun
01:40 – 01:50 GMT
Closing Remarks
Iterative Value Learning for ThroughputOptimization of Deep Learning Workloads
Benoit Steiner