Skip to content
GCC AI Research

Search

Results for "bandit feedback"

Discrete and Continuous Submodular Bandits with Full Bandit Feedback

MBZUAI ·

Vaneet Aggarwal from Purdue University presented new research on discrete and continuous submodular bandits with full bandit feedback. The research introduces a framework transforming discrete offline approximation algorithms into sublinear α-regret methods using bandit feedback. Additionally, it introduces a unified approach for maximizing continuous DR-submodular functions, accommodating various settings and oracle access types. Why it matters: This research provides new methods for optimization under uncertainty, which is crucial for real-world AI applications in the region, such as resource allocation and automated decision-making.

Fine-tuning Text-to-Image Models: Reinforcement Learning and Reward Over-Optimization

MBZUAI ·

The article discusses research on fine-tuning text-to-image diffusion models, including reward function training, online reinforcement learning (RL) fine-tuning, and addressing reward over-optimization. A Text-Image Alignment Assessment (TIA2) benchmark is introduced to study reward over-optimization. TextNorm, a method for confidence calibration in reward models, is presented to reduce over-optimization risks. Why it matters: Improving the alignment and fidelity of text-to-image models is crucial for generating high-quality content, and addressing over-optimization enhances the reliability of these models in creative applications.

Learning to act in noisy contexts using deep proxy learning

MBZUAI ·

Researchers are exploring methods for evaluating the outcome of actions using off-policy observations where the context is noisy or anonymized. They employ proxy causal learning, using two noisy views of the context to recover the average causal effect of an action without explicitly modeling the hidden context. The implementation uses learned neural net representations for both action and context, and demonstrates outperformance compared to an autoencoder-based alternative. Why it matters: This research addresses a key challenge in applying AI in real-world scenarios where data privacy or bandwidth limitations necessitate working with noisy or anonymized data.

When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards

arXiv ·

Researchers from the National Center for AI in Saudi Arabia investigated the sensitivity of Large Language Model (LLM) leaderboards to minor benchmark perturbations. They found that small changes, like choice order, can shift rankings by up to 8 positions. The study recommends hybrid scoring and warns against over-reliance on simple benchmark evaluations, providing code for further research.

The search for an antidote to Byzantine attacks

MBZUAI ·

MBZUAI researchers have developed 'Byzantine antidote' (Bant), a novel defense mechanism against Byzantine attacks in federated learning. Bant uses trust scores and a trial function to dynamically filter and neutralize corrupted updates, even when a majority of nodes are compromised. The research was presented at the 40th Annual AAAI Conference on Artificial Intelligence.

Fast Rates for Maximum Entropy Exploration

MBZUAI ·

This paper addresses exploration in reinforcement learning (RL) in unknown environments with sparse rewards, focusing on maximum entropy exploration. It introduces a game-theoretic algorithm for visitation entropy maximization with improved sample complexity of O(H^3S^2A/ε^2). For trajectory entropy, the paper presents an algorithm with O(poly(S, A, H)/ε) complexity, showing the statistical advantage of regularized MDPs for exploration. Why it matters: The research offers new techniques to reduce the sample complexity of RL, potentially enhancing the efficiency of AI agents in complex environments.

Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box Optimization

arXiv ·

This paper introduces Diffusion-BBO, a new online black-box optimization (BBO) framework that uses a conditional diffusion model as an inverse surrogate model. The framework employs an Uncertainty-aware Exploration (UaE) acquisition function to propose scores in the objective space for conditional sampling. The approach is shown theoretically to achieve a near-optimal solution and empirically outperforms existing online BBO baselines across 6 scientific discovery tasks.

Finding true protein hotspots in cancer research

KAUST ·

KAUST researchers developed a statistical approach to improve the identification of cancer-related protein mutations by reducing false positives. The method uses Bayesian statistics to analyze protein domain data from tumor samples, accounting for potential errors due to limited data. The team tested their method on prostate cancer data, successfully identifying a known cancer-linked mutation in the DNA binding protein cd00083. Why it matters: This enhances the reliability of cancer research at the molecular level, potentially accelerating the discovery of new therapeutic targets.