Zobrazeno 1 - 10
of 386
pro vyhledávání: '"Panangaden, P."'
Autor:
Burton, Peter, Panangaden, Jane
Furstenberg's $\times 2 \times 3$ conjecture has remained a central open problem in ergodic theory for over $50$ years, and it serves as the basic test case for a broad class of rigidity phenomena which are believed to hold in number-theoretic dynami
Externí odkaz:
http://arxiv.org/abs/2410.22701
We study Polynomial Lawvere logic PL, a logic defined over the Lawvere quantale of extended positive reals with sum as tensor, to which we add multiplication, thereby obtaining a semiring structure. PL is designed for complex quantitative reasoning,
Externí odkaz:
http://arxiv.org/abs/2402.03543
Bisimulation is a concept that captures behavioural equivalence of states in a variety of types of transition systems. It has been widely studied in a discrete-time setting where the notion of a step is fundamental. In our setting we are considering
Externí odkaz:
http://arxiv.org/abs/2312.16729
Learning from Preferential Feedback (LfPF) plays an essential role in training Large Language Models, as well as certain types of interactive learning agents. However, a substantial gap exists between the theory and application of LfPF algorithms. Cu
Externí odkaz:
http://arxiv.org/abs/2311.01990
Autor:
Panangaden, Jane
We begin with the higher-weight modular symbols introduced by Shokurov, which generalize Manin's weight-2 modular symbols. We then define higher-weight limiting modular symbols associated to vertical geodesics with one endpoint at an irrational real
Externí odkaz:
http://arxiv.org/abs/2310.12468
Behavioural metrics have been shown to be an effective mechanism for constructing representations in reinforcement learning. We present a novel perspective on behavioural metrics for Markov decision processes via the use of positive definite kernels.
Externí odkaz:
http://arxiv.org/abs/2310.19804
In this paper, we study the approximate minimization problem of weighted finite automata (WFAs): to compute the best possible approximation of a WFA given a bound on the number of states. By reformulating the problem in terms of Hankel matrices, we l
Externí odkaz:
http://arxiv.org/abs/2306.00135
Reinforcement learning (RL) on high-dimensional and complex problems relies on abstraction for improved efficiency and generalization. In this paper, we study abstraction in the continuous-control setting, and extend the definition of Markov decision
Externí odkaz:
http://arxiv.org/abs/2305.05666
Publikováno v:
Electronic Notes in Theoretical Informatics and Computer Science, Volume 3 - Proceedings of MFPS XXXIX (November 23, 2023) entics:12292
Lawvere showed that generalised metric spaces are categories enriched over $[0, \infty]$, the quantale of the positive extended reals. The statement of enrichment is a quantitative analogue of being a preorder. Towards seeking a logic for quantitativ
Externí odkaz:
http://arxiv.org/abs/2302.01224