A quick guide to Amazon's papers on Neurips 2023

A quick guide to Amazon’s papers on Neurips 2023

by

The conference on neural information treatment systems (Neurips) takes place this week, and Amazon Papers’ acceptance that touches on a wide range of topics, from experimental design and human-robot interaction to recommendation systems and statistical estimation in real time. In the midst of this diversity, a few topics come in for special attention: optimization, privacy, table-shaped data, time series forecasts, vision-warming models and especially reinforcing learning.

Generation code

Large Language Models of Code Failing by Completing Code with Potential Errors
Tuan Dinh, Jinman Zhao, Samson Tan, Renato Negrinho, Leonard Lausen, Sheng Zha, George Karypis

Complex query response

Complex inquiry that responds to graph of events of events with implicit logical restrictions
Jiaxin Bai, Xin Liu, Weiqi Wang, Chen Luo, Yangqiu Song

An example of a complex eventuality Inquiry with its computational and informative atomic. V Is something that happens before a person complains and leaves a restaurant; As per the Knowledge Graph, V Could be either “service is bad” or “food is bad”. If V? is the reason Vso according to the graph, V? Could be either “staff is new”, “Persony adds ketchup”, “Persony adds soy sauce” or “Persony adds vinegar”. From the inquiry, however, we know that “personal adds vinegar” does not happen, and “personically adds soy sauce” happens after “food is bad”, so that may be the reason “food is bad”. From “Complex Inquiry that responds to the event graph of eventuality with implicit logical limitations”.

Experimental design

Experimental designs for heteroskedastic variance
Justin Weltz, Tanner Fiez, Eric Laber, Alexander Volfovsky, Blake Mason, Houssam Nassif, Lalit Jain

Federated Learning

Federated Multi-Lens Learning
Haibo Yang, Zhuqing Liu, Jia Liu, Chaosheng Dong, Michinari Mimage

Human-robot interaction

Alexa Arena: A user -centrical interactive platform for embodied AI
Qiaozi (QZ) Gao, Govind Thattai, Suhaila Shakiah, Xiaofeng Gao, Shreyas Pansare, Vasu Sharma, Gaurav Sukhatme, Hangjie Shi, Bofei Yang, Desheng Zhang, Lucy Hu, Karthika Arumugam, Shui Hu, Matthew Wenwew Weny, Dinakar Guty Chung, Rohan Khanna, Osman Ipek, Leslie Ball, Kate Bland, Heather Rocker, Michael Johnston, Reza Ghanadan, Dilek Hakkani-Tür, Prem Natarajan

Optimization

BOUNCE: DEFABLE HIGH-DIMENSAL BAYESIAN OPDINGS TO Combinatories and mixed spaces
Leonard Papenmeier, Luigi Nardi, Matthias Poloczek

Debiassing -mode stoccastic optimization
Lies he, shiva kasiviswanathan

Distribution Robust Bayesian optimization with φ deviations
Hisham Husain, Set Nguyen, Anton Van Den Hengel

Ordinal classification

Conservation Present Set for Ordinal Classification
Prasenjit dey, Srujana Merugu, Sivaramakrishnan (Siva) Kaveri

Privacy

Creating a Public Restity to participate in Private Data
James Cook, Milind Shyani, Nina Mishra

A stylized illustration of the restity problem. The sender S. Uploads a private country sketch that catches that people do and have no cancer. The recipient R. the sketch to decorate her data (people’s work rental) with a noisy version of S.‘S cancer column. Two noisy columns are generated: one for cancer (+1) and one for not (–1). R. Can then build a machine learning model to predict where the employee working near a toxic was the place, is more likely to develop cancer. From “Creating a public restity to participate in private data”.

Scalable membership of membership events via quantity regression
Martin Bertran Lopez, Shuai Tang, Michael Kearns, Jamie Morgenstern, Aaron Roth, Zhiwei Steven Wu

Statistical Estimate in real time

Robust online non-indulgencing estimate
Abishek Sankararaman, Balakrishnan (Murali) Narayanaswamy

Recumend systems

Improving user interest in session -based recommendation with attribut patterns
Xin Liu, Zheng Li, Yifan Gao, Jingfeng Yang, Tiunyu Cao, Zhengyang Wang, Bing Yin, Yangqiu Song

Reinforcement learning

Budgeting of counterfactual for offline rl
Yao Liu, Pratik Chaudhari, Rasool Fakoor

End Time Logarithmic Bayes Sorry for Upper Borders
Alexia Atsidakou, Branislav Kveton, Sumeet Katariya, Constantine Caramanis, Sujay Sanghavi

Resetting Optimizer in Deep RL: an empirical examination
Kavosh Asadi, Rasool Fakoor, Shoham Sabach

TD -Convergence: An Optimization Perspective
Kavosh Asadi, Shoham Sabach, Yao Liu, Omer Gottesman, Rasool Fakoor

AI Responsible

Improving justice of spoken language understanding in atypical talk with text-to-speech
Helin Wang, Venkatesh Ravichandran, Milind Rao, Becky Lammers, Myra Sydnor, Nicholas Maragakis, Ankur A. Butala, Jayne Zhang, Victoria Chovaz, Laureano Moro-Velazquezquez

Tabular data

An inductive bias for table -shaped deep learning
Ege Beyazit, Jonathan Kozaczuk, Bo Li, Vanessa Wallace, Bilal Fadlallah

Hytrel: Hypergraph-enhanced tabular date-presenting learning
Pei Chen, Soumajyoti Sarkar, Leonard Lausen, Balasubramaniam Srinivasan, Sheng Zha, Ruihong Huang, George Karypis

An example of modeling a table like a hypergraf. Cells make up the nodes and the cells in each row, each column and the entire table form hyperedges. Table -image text and heading names give the names of the table and column hyperedges. The hypergrafen holds the four structural properties of tables – ie. Row/column permutations result in the same hypergraf. From “Hytrel: Hypergraph-enhanced tabular date presentation learning”.

Forecasts for time series

Predict, refine, synthesize: Self -controlling diffusion models for forecasts for probabilistic time series
Marcel Kollovieh, Abdul Fatir Ansari, Michael Bohlke-Schneider, Jasper Zschiegner, Hao Wang, Yuyang (Bernie) Wang

Prediff: precipitation nucasting with latent diffusion models
Zhihan Gao, Xingjian Shi, Boran Han, Hao Wang, Xiaoyong Jin, Danielle Maddix Robinson, Yi Zhu, Mu Li, Yuyang (Bernie) Wang

Vision-language models

Quick pre-formation with twenty thousand classes for open-vocabulary Visual Recognition
Shuhuai Ren, Aston Zhang, Yi Zhu, Shuai Zhang, Shuai Zheng, Mu Li, Alex Smola, Xu Su

Your representations are in the network: composed and parallel adaptation to models on a large scale
Yonatan Dolls, Alessandro Achille, Hao Yang, Ben Bowman, Varsha Vivek, Luca Zancato, Avinash Ravichandran, Charless Fowlkes, Ashwin Swaminathan, Stefano Soatto

Leave a Comment