The Optimal Sample Complexity of PAC Learning
نویسنده
چکیده
This work establishes a new upper bound on the number of samples sufficient for PAC learning in the realizable case. The bound matches known lower bounds up to numerical constant factors. This solves a long-standing open problem on the sample complexity of PAC learning. The technique and analysis build on a recent breakthrough by Hans Simon.
منابع مشابه
Active and passive learning of linear separators under log-concave distributions
We provide new results concerning label efficient, polynomial time, passive and active learning of linear separators. We prove that active learning provides an exponential improvement over PAC (passive) learning of homogeneous linear separators under nearly log-concave distributions. Building on this, we provide a computationally efficient PAC algorithm with optimal (up to a constant factor) sa...
متن کاملThe Optimal Distribution-Free Sample Complexity of Distribution-Dependent Learning
This work establishes a new upper bound on the worst-case number of labeled samples sufficient for PAC learning in the realizable case, if the learning algorithm is allowed dependence on the data distribution, or an additional pool of unlabeled samples. The bound matches known lower bounds up to constant factors. This resolves a long-standing open problem on the sample complexity of distributio...
متن کاملSample Efficient Reinforcement Learning with Gaussian Processes
This paper derives sample complexity results for using Gaussian Processes (GPs) in both modelbased and model-free reinforcement learning (RL). We show that GPs are KWIK learnable, proving for the first time that a model-based RL approach using GPs, GP-Rmax, is sample efficient (PAC-MDP). However, we then show that previous approaches to model-free RL using GPs take an exponential number of step...
متن کاملSample Complexity Bounds of Exploration
Efficient exploration is widely recognized as a fundamental challenge inherent in reinforcement learning. Algorithms that explore efficiently converge faster to near-optimal policies. While heuristics techniques are popular in practice, they lack formal guarantees and may not work well in general. This chapter studies algorithms with polynomial sample complexity of exploration, both model-based...
متن کاملPAC Reinforcement Learning Bounds for RTDP and Rand-RTDP
Real-time Dynamic Programming (RTDP) is a popular algorithm for planning in a Markov Decision Process (MDP). It can also be viewed as a learning algorithm, where the agent improves the value function and policy while acting in an MDP. It has been empirically observed that an RTDP agent generally performs well when viewed this way, but past theoretical results have been limited to asymptotic con...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Journal of Machine Learning Research
دوره 17 شماره
صفحات -
تاریخ انتشار 2016