paper-with-me

홈 › Papers

Local large deviations for linear-region growth in random piecewise-linear networks

2026-07-08 · Recep Özkan, Christian Hirsch arxiv

We study a random compositional model for the growth of affine regions in deep piecewise-linear networks. The model is generated by i.i.d.\ perturbations of the symmetric height-one tent map, and the main observable is the number \(N_n\) of affine pieces after \(n\) layers. We prove the existence of a submultiplicative pressure for \(N_n\), yielding exponential upper bounds for both tails of \(n^{-1}\log N_n\). The same argument applies to abstract submultiplicative complexity observables and gives higher-dimensional extensions for convex-polytopal affine-cover counts and worst-line affine-piece counts. Since the true branch count has no matching supermultiplicative inequality, lower bounds require a separate certified construction. We introduce a finite-state defect process that records branches whose future splitting can be guaranteed, and use bridge words to obtain constructive upper-tail lower bounds. In a uniformly favorable small-noise regime, this process is governed by a companion matrix whose Perron root tends to \(2\), implying eventual exclusion of lower tails below \(\log 2-ξ\).

📄 PDF Abstract BibTeX arXiv:2607.07014

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Ergodic robust maximization of asymptotic growth

2018-01-19

We consider the problem of robustly maximizing the growth rate of investor wealth in the presence of model uncertainty. Possible models are all those under which the assets' region $E$ and instantaneous covariation $c$ a…

NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search

2026-05-01 · Sizhe Tang, Zuyuan Zhang, Mahdi Imani, Tian Lan arxiv

Monte Carlo Tree Search (MCTS) scales poorly in cooperative multi-agent domains because expansion must consider an exponentially large set of joint actions, severely limiting exploration under realistic search budgets. W…

What is the long-run distribution of stochastic gradient descent? A large deviations analysis

2024-06-13 · Waïss Azizian, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos

In this paper, we examine the long-run distribution of stochastic gradient descent (SGD) in general, non-convex problems. Specifically, we seek to understand which regions of the problem's state space are more likely to …

Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol

2026-02-10 · Flint Xiaofeng Fan, Cheston Tan, Roger Wattenhofer, Yew-Soon Ong arxiv

As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce t…

Semantic Similarity

Measurement of Economic Growth, Development and Under Development: New Model and Application

2017-04-17

This paper presents a simple model to measure the relative economic growth of economic systems. The model considers S-Shaped patterns of economic growth that, represented with a linear model, measure how an economic syst…