Learning The Best Expert Efficiently
We consider online learning problems where the aim is to achieve regret which is efficient in the sense that it is the same order as the lowest regret amongst K experts. This is a substantially stronger requirement that achieving $O(\sqrt{n})$ or $O(\log n)$ regret with respect to the best expert and standard algorithms are insufficient, even in easy cases where the regrets of the available actions are very different from one another. We show that a particular lazy form of the online subgradient algorithm can be used to achieve minimal regret in a number of "easy" regimes while retaining an $O(\sqrt{n})$ worst-case regret guarantee. We also show that for certain classes of problem minimal regret strategies exist for some of the remaining "hard" regimes.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Hierarchically Gated Experts for Efficient Online Continual Learning
Continual Learning models aim to learn a set of tasks under the constraint that the tasks arrive sequentially with no way to access data from previous tasks. The Online Continual Learning framework poses a further challe…
Continual LearningIdentifiability of Product of Experts Models
Product of experts (PoE) are layered networks in which the value at each node is an AND (or product) of the values (possibly negated) at its inputs. These were introduced as a neural network architecture that can efficie…
Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models
We propose MoE-F - a formalized mechanism for combining $N$ pre-trained Large Language Models (LLMs) for online time-series prediction by adaptively forecasting the best weighting of LLM predictions at every time step. O…
Mixture-of-ExpertsTime SeriesTime Series ForecastingTime Series PredictionAcquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts
Reinforcement learning (RL) is a powerful approach for acquiring a good-performing policy. However, learning diverse skills is challenging in RL due to the commonly used Gaussian policy parameterization. We propose \text…
Mixture-of-ExpertsReinforcement Learning (RL)Exploiting Sample Correlation for Crowd Counting With Multi-Expert Network
Crowd counting is a difficult task because of the diversity of scenes. Most of the existing crowd counting methods adopt complex structures with massive backbones to enhance the generalization ability. Unfortunately,…
Crowd Counting