Faster Rates for Private Adversarial Bandits

We design new differentially private algorithms for the problems of adversarial bandits and bandits with expert advice. For adversarial bandits, we give a simple and efficient conversion of any non-private bandit algorithms to private bandit algorithms. Instantiating our conversion with existing non-private bandit algorithms gives a regret upper bound of O(KTε)Oleft(frac{sqrt{KT}}{sqrt{varepsilon}}right)O(ε​KT​​), improving upon the existing …

image ML 18195 1

How INRIX accelerates transportation planning with Amazon Bedrock

This post is co-written with Shashank Saraogi, Nat Gale, and Durran Kelly from INRIX. The complexity of modern traffic management extends far beyond mere road monitoring, encompassing massive amounts of data collected worldwide from connected cars, mobile devices, roadway sensors, and major event monitoring systems. For transportation authorities managing urban, suburban, and rural traffic flow, …

Approach improves how new skills are taught to large language models

Researchers have developed a technique that significantly improves the performance of large language models without increasing the computational power necessary to fine-tune the models. The researchers demonstrated that their technique improves the performance of these models over previous techniques in tasks including commonsense reasoning, arithmetic reasoning, instruction following, code generation, and visual recognition.

Full Breakdown: The bghira/Simpletuner Situation

I wanted to provide a detailed timeline of recent events concerning bghira, the creator of the popular LoRA training tool, Simpletuner. Things have escalated quickly, and I believe the community deserves to be aware of the full situation. TL;DR: The creator of Simpletuner, bghira, began mass-reporting NotSFW LoRAs on Hugging Face. When called out, he …