Probability Tools for Sequential Random Projection
Abstract: We introduce the first probabilistic framework tailored for sequential random projection, an approach rooted in the challenges of sequential decision-making under uncertainty. The analysis is complicated by the sequential dependence and high-dimensional nature of random variables, a byproduct of the adaptive mechanisms inherent in sequential decision processes. Our work features a novel construction of a stopped process, facilitating the analysis of a sequence of concentration events that are interconnected in a sequential manner. By employing the method of mixtures within a self-normalized process, derived from the stopped process, we achieve a desired non-asymptotic probability bound. This bound represents a non-trivial martingale extension of the Johnson-Lindenstrauss (JL) lemma, marking a pioneering contribution to the literature on random projection and sequential analysis.
- Dimitris Achlioptas. Database-friendly random projections: Johnson-lindenstrauss with binary coins. Journal of computer and System Sciences, 66(4):671–687, 2003.
- A simple proof of the restricted isometry property for random matrices. Constructive approximation, 28:253–263, 2008.
- Near-optimal signal recovery from random projections: Universal encoding strategies? IEEE transactions on information theory, 52(12):5406–5425, 2006.
- Simple analyses of the sparse johnson-lindenstrauss transform. In 1st Symposium on Simplicity in Algorithms (SOSA 2018). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, 2018.
- Self-normalized processes: Exponential inequalities, moment bounds and iterated logarithm laws. Annals of Probability, pages 1902–1933, 2004.
- Self-normalized processes: Limit theory and Statistical Applications. Springer, 2009.
- Piotr Indyk. Algorithmic applications of low-distortion embeddings. In Proc. 42nd IEEE Symposium on Foundations of Computer Science, page 1, 2001.
- Approximate nearest neighbors: towards removing the curse of dimensionality. In Proceedings of the thirtieth annual ACM symposium on Theory of computing, pages 604–613, 1998.
- Extensions of lipschitz mappings into a hilbert space. In Conference on Modern Analysis and Probability, volume 26, pages 189–206. American Mathematical Society, 1984.
- Sparser johnson-lindenstrauss transforms. Journal of the ACM (JACM), 61(1):1–23, 2014.
- Tze Leung Lai. Martingales in sequential analysis and time series, 1945-1985. In Electronic Journal for history of probability and statistics, 2009.
- Yingru Li. Simple, unified analysis of johnson-lindenstrauss with applications, 2023. To appear on arXiv preprint.
- Efficient and scalable reinforcement learning via hypermodel. In NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World, 2023. URL https://openreview.net/forum?id=juq0ZUWOoY.
- Hyperagent: A simple, scalable, efficient and provable reinforcement learning framework for complex environments, 2024. To appear on arXiv preprint.
- HyperDQN: A randomized exploration method for deep reinforcement learning. In International Conference on Learning Representations, 2022. URL https://openreview.net/forum?id=X0nrKAXu7g-.
- Jiřà Matoušek. On variants of the johnson–lindenstrauss lemma. Random Structures & Algorithms, 33(2):142–156, 2008.
- Shanmugavelayutham Muthukrishnan et al. Data streams: Algorithms and applications. Foundations and Trends® in Theoretical Computer Science, 1(2):117–236, 2005.
- Boundary crossing probabilities for the wiener process and sample sums. The Annals of Mathematical Statistics, pages 1410–1429, 1970.
- Maciej Skorski. Bernstein-type bounds for beta distribution. Modern Stochastics: Theory and Applications, 10(2):211–228, 2023.
- Roman Vershynin. Introduction to the non-asymptotic analysis of random matrices. In Yonina C. Eldar and Gitta Kutyniok, editors, Compressed Sensing: Theory and Applications, page 210–268. Cambridge University Press, 2012. doi: 10.1017/CBO9780511794308.006.
- David P Woodruff et al. Sketching as a tool for numerical linear algebra. Foundations and Trends® in Theoretical Computer Science, 10(1–2):1–157, 2014.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
