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

Workshop: ML Retrospectives, Surveys & Meta-Analyses (ML-RSA)

Chhavi Yadav, Prabhu Pradhan, Abhishek Gupta, Jesse Dodge, Mayoore Jaiswal, Peter Henderson, Ryan Lowe, Jessica Forde Jessica Forde

2020-12-11T08:30:00-08:00 - 2020-12-11T21:00:00-08:00
Abstract: The exponential growth of AI research has led to several papers floating on arxiv, making it difficult to review existing literature. Despite the huge demand, the proportion of survey & analyses papers published is very low due to reasons like lack of a venue and incentives. Our Workshop, ML-RSA provides a platform and incentivizes writing such types of papers. It meets the need of taking a step back, looking at the sub-field as a whole and evaluating actual progress. We will accept 3 types of papers: broad survey papers, meta-analyses, and retrospectives. Survey papers will mention and cluster different types of approaches, provide pros and cons, highlight good source code implementations, applications and emphasize impactful literature. We expect this type of paper to provide a detailed investigation of the techniques and link together themes across multiple works. The main aim of these will be to organize techniques and lower the barrier to entry for newcomers. Meta-Analyses, on the other hand, are forward-looking, aimed at providing critical insights on the current state-of-affairs of a sub-field and propose new directions based on them. These are expected to be more than just an ablation study -- though an empirical analysis is encouraged as it can provide for a stronger narrative. Ideally, they will seek to showcase trends that are not possible to be seen when looking at individual papers. Finally, retrospectives seek to provide further insights ex post by the authors of a paper: these could be technical, insights into the research process, or other helpful information that isn’t apparent from the original work.

Chat

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

Schedule

2020-12-11T08:30:00-08:00 - 2020-12-11T08:55:00-08:00
Introduction
2020-12-11T09:00:00-08:00 - 2020-12-11T09:30:00-08:00
Invited: Shakir Mohamed
Shakir Mohamed
2020-12-11T09:35:00-08:00 - 2020-12-11T09:45:00-08:00
Q&A 1
Shakir Mohamed
2020-12-11T10:00:00-08:00 - 2020-12-11T10:55:00-08:00
Brainstorming
2020-12-11T10:55:00-08:00 - 2020-12-11T11:00:00-08:00
Intro to speaker 2 : Kilian Weinberger
2020-12-11T11:00:00-08:00 - 2020-12-11T11:30:00-08:00
Invited: Kilian Weinberger
Kilian Weinberger
2020-12-11T11:35:00-08:00 - 2020-12-11T11:45:00-08:00
Q&A 2
Kilian Weinberger
2020-12-11T12:00:00-08:00 - 2020-12-11T12:45:00-08:00
Panel
2020-12-11T12:55:00-08:00 - 2020-12-11T13:00:00-08:00
Intro to speaker 3 Maria De-Artega
2020-12-11T13:00:00-08:00 - 2020-12-11T13:30:00-08:00
Invited: Maria De-Artega
Maria De-Arteaga
2020-12-11T13:35:00-08:00 - 2020-12-11T13:45:00-08:00
Q&A 3
Maria De-Arteaga
2020-12-11T13:55:00-08:00 - 2020-12-11T14:00:00-08:00
Intro to speaker 4 : Shibani Santurkar
2020-12-11T14:00:00-08:00 - 2020-12-11T14:30:00-08:00
Invited: Shibani Santurkar
Shibani Santurkar
2020-12-11T14:35:00-08:00 - 2020-12-11T14:45:00-08:00
Q&A 4
Shibani Santurkar
2020-12-11T14:55:00-08:00 - 2020-12-11T15:00:00-08:00
Poster Session Starts
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Towards falsifiable interpretability research
Matthew L Leavitt
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
WILDS: A Survey and Benchmark of in-the-Wild Distribution Shifts
Pang Wei Koh
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
The Hardware Lottery
Sara Hooker
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Data and its (dis)contents: A survey of dataset development and use in machine learning research
Amandalynne Paullada
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Challenges in Deploying Machine Learning: a Survey of Case Studies
Andrei Paleyes
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
A Survey of Machine Learning Methods and Challenges for Windows Malware Classification
Edward Raff
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
Amir Karimi
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Opportunities for a More Interdisciplinary Approach to Perceptions of Fairness in Machine Learning
Sarah Brown
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Understanding Attention: In Minds and Machines
Shri Sawant
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Counterfactual Explanations for Machine Learning: A Review
Sahil Verma
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
A Brief Survey of Loop Closure Detection: A Case for Rethinking Evaluation of Intelligent Systems
Samer Nashed
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Deconstructing the Structure of Sparse Neural Networks
Maxwell D Van Gelder
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Revisiting "Qualitatively Characterizing Neural Network Optimization Problems"
Jonathan Frankle
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Feature Removal Is a Unifying Principle For Model Explanation Methods
Ian Covert
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages
Kushal Jain
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
On Principles, Models and Methods for Learning from Irregularly Sampled Time Series...
Satya Narayan Shukla
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
A Survey of Deep Learning Approaches for OCR and Document Understanding
Nishant Subramani
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Challenging common interpretability assumptions in feature attribution explanations
Jonathan Dinu
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Beyond Methods Reproducibility in Machine Learning
Leif Hancox-Li
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Pruning Neural Networks at Initialization: Why Are We Missing the Mark?
Jonathan Frankle
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
Survey on Modeling Intensity Function of Hawkes Process Using Neural Models
Jayesh Malaviya
2020-12-11T15:00:00-08:00 - 2020-12-11T16:45:00-08:00
AI and the Everything in the Whole Wide World Benchmark
Deborah Raji
2020-12-11T16:55:00-08:00 - 2020-12-11T17:00:00-08:00
Intro to speaker 5 : Lana Sinapayen
2020-12-11T17:00:00-08:00 - 2020-12-11T17:30:00-08:00
Invited: Lana Sinapayen
Lana Sinapayen
2020-12-11T17:35:00-08:00 - 2020-12-11T17:45:00-08:00
Q&A 5
Lana Sinapayen
2020-12-11T17:55:00-08:00 - 2020-12-11T18:00:00-08:00
Intro to Speaker 6 : Reza Shokri
2020-12-11T18:00:00-08:00 - 2020-12-11T18:30:00-08:00
Invited: Reza Shokri
Reza Shokri
2020-12-11T18:35:00-08:00 - 2020-12-11T18:45:00-08:00
Q&A 6
Reza Shokri
2020-12-11T19:00:00-08:00 - 2020-12-11T20:00:00-08:00
Awardees' Talks
2020-12-11T20:00:00-08:00 - 2020-12-11T20:05:00-08:00
Closing