Friday, February 7, 2025

Artificial Intelligence news

These documents are influencing...

Reports from the US Government Accountability Office on improper federal payments in...

Reframing digital transformation through...

Enterprise adoption of generative AI technologies has undergone explosive growth in the...

An AI chatbot told...

For the past five months, Al Nowatzki has been talking to an...

What’s next for smart...

MIT Technology Review’s What’s Next series looks across industries, trends, and technologies...
HomeMachine LearningNear-Optimal Algorithms for...

Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime



*=Equal Contributors
We consider online learning problems in the realizable setting, where there is a zero-loss solution, and propose new Differentially Private (DP) algorithms that obtain near-optimal regret bounds. For the problem of online prediction from experts, we design new algorithms that obtain near-optimal regret where is the number of experts. This significantly improves over the best existing regret bounds for the DP non-realizable setting which are . We also develop an adaptive algorithm for the small-loss setting with regret where is the total loss of the best expert…



Article Source link and Credit

Continue reading

Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization

Machine Translation (MT) is undergoing a paradigm shift, with systems based on fine-tuned large language models (LLM) becoming increasingly competitive with traditional encoder-decoder models trained specifically for translation tasks. However, LLM-based systems are at a higher risk of...

Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models

Scaling the capacity of language models has consistently proven to be a reliable approach for improving performance and unlocking new capabilities. Capacity can be primarily defined by two dimensions: the number of model parameters and the compute per example. While...

Compact Neural TTS Voices for Accessibility

Contemporary text-to-speech solutions for accessibility applications can typically be classified into two categories: (i) device-based statistical parametric speech synthesis (SPSS) or unit selection (USEL) and (ii) cloud-based neural TTS. SPSS and USEL offer low latency and low disk...