dbos – Page 35 – Kavli Institute Pre-Print Publications

Independently-Normalized SGD for Generalized-Smooth Nonconvex Optimization

Posted by dbos October 17, 2024October 28, 2024UCAS

Kavli Affiliate: Yi Zhou | First 5 Authors: Yufeng Yang, Erin Tripp, Yifan Sun, Shaofeng Zou, Yi Zhou | Summary: Recent studies have shown that many nonconvex machine learning problems meet a so-called generalized-smooth condition that extends beyond traditional smooth nonconvex optimization. However, the existing algorithms designed for generalized-smooth nonconvex optimization encounter significant limitations in […]

Continue..

Optimal Communication and Key Rate Region for Hierarchical Secure Aggregation with User Collusion

Posted by dbos October 17, 2024October 28, 2024Berkeley

Kavli Affiliate: Xiang Zhang | First 5 Authors: Xiang Zhang, Kai Wan, Hua Sun, Shiqiang Wang, Mingyue Ji | Summary: Secure aggregation is concerned with the task of securely uploading the inputs of multiple users to an aggregation server without letting the server know the inputs beyond their summation. It finds broad applications in distributed […]

Continue..

Optimal Communication and Key Rate Region for Hierarchical Secure Aggregation with User Collusion

Posted by dbos October 17, 2024Berkeley

Continue..

Optimal Communication and Key Rate Region for Hierarchical Secure Aggregation with User Collusion

Posted by dbos October 17, 2024Berkeley

Continue..

GRB Redshift Estimation using Machine Learning and the Associated Web-App

Posted by dbos October 17, 2024October 28, 2024Stanford

Kavli Affiliate: Vahe Petrosian | First 5 Authors: Aditya Narendra, Maria Dainotti, Milind Sarkar, Aleksander Lenart, Malgorzata Bogdan | Summary: Context. Gamma-ray bursts (GRBs), observed at redshifts as high as 9.4, could serve as valuable probes for investigating the distant Universe. However, this necessitates an increase in the number of GRBs with determined redshifts, as […]

Continue..

Trojan Prompt Attacks on Graph Neural Networks

Posted by dbos October 17, 2024October 28, 2024Berkeley

Kavli Affiliate: Xiang Zhang | First 5 Authors: Minhua Lin, Zhiwei Zhang, Enyan Dai, Zongyu Wu, Yilong Wang | Summary: Graph Prompt Learning (GPL) has been introduced as a promising approach that uses prompts to adapt pre-trained GNN models to specific downstream tasks without requiring fine-tuning of the entire model. Despite the advantages of GPL, […]

Continue..

Role of dopamine in reward expectation and predictability during execution of action sequences

Posted by dbos October 17, 2024October 28, 2024Hopkins

Kavli Affiliate: Patricia Janak | Authors: Robin Magnard, Yifeng Cheng, Joanna Zhou, Haley Province, Nathalie Thiriet, Patricia H Janak and Youna Vandaele | Summary: Reward-associated cues serve different functions depending on whether they precede or terminate action sequences. Cues that precede action sequences and signal opportunity for reward could serve as GO signals to initiate […]

Continue..

SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction

Posted by dbos October 17, 2024October 28, 2024Caltech

Kavli Affiliate: Wei Gao | First 5 Authors: Xuan Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao | Summary: Recent advancements in large language models (LLMs) have extended their capabilities to handle long contexts. However, increasing the number of model layers and the length of input sequences significantly escalates the memory required to store […]

Continue..

The Affleck-Dine Curvaton

Posted by dbos October 17, 2024October 28, 2024Chicago

Kavli Affiliate: Gordan Krnjaic | First 5 Authors: Aurora Ireland, Gordan Krnjaic, Takuya Okawa, , | Summary: The Standard Model of particle physics does not explain the origin of the universe’s baryon asymmetry or its primordial fluctuations. The Affleck-Dine mechanism is a well-motivated scenario for generating the baryon asymmetry through the post-inflationary dynamics of a […]

Continue..

ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization

Posted by dbos October 17, 2024October 28, 2024Peking

Kavli Affiliate: Ke Wang | First 5 Authors: Xiutian Zhao, Ke Wang, Wei Peng, , | Summary: Dialogue agents have been receiving increasing attention for years, and this trend has been further boosted by the recent progress of large language models (LLMs). Stance detection and dialogue summarization are two core tasks of dialogue agents in […]

Continue..