Philipp Tuchel

activity

20242026

most citedA Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption

8 citations · 8 across the 8 of their papers we have counts for

collaborators

8 papers

math.PR2026

Realising atomless laws as distance distributions on metric measure spaces

Christoph Thäle, Philipp Tuchel

We study which probability measures on $[0, \infty)$ can occur as the distribution of the distance between two independent points sampled from a complete separable metric space equi…

math.PR2026

Mod-phi convergence for random variables with cyclotomic generating functions

Christoph Thäle, Philipp Tuchel

We consider a sequence of discrete random variables whose generating functions are polynomials only having roots on the unit circle in the complex plane. For such sequences we prov…

math.HO2026

Benchmarks in Leipzig

Andrei Balakin, Miklós Bóna, Marie-Charlotte Brandenburg +45

Between April 1 and May 15, 2026, a group of 49 mathematicians compiled a dataset of research-level mathematics questions with known answers. Most of the work was done during the t…

math.PR2026

Large deviations for sums of multivariate stretched-exponential random variables: the few-big-jumps principle

Nina Gantert, Joscha Prochno, Philipp Tuchel

Large deviations for sums of i.i.d.\ random variables with stretched-exponential tails (also called Weibull or semi-exponential tails) have been well understood since the 60's, goi…

cs.NE2025

On the Universal Representation Property of Spiking Neural Networks

Shayan Hundrieser, Philipp Tuchel, Insung Kong +1

Inspired by biology, spiking neural networks (SNNs) process information via discrete spikes over time, offering an energy-efficient alternative to the classical computing paradigm…

math.PR2025

Large and Moderate Deviations for Entries of Orthogonal Matrices and the Stiefel Manifold

Philipp Tuchel

Let $A_{N}$ be distributed according to the Haar probability measure on the orthogonal group $O (N)$ for each $N \in N$ . It is well-known that the upper left $m_N\tim…

math.PR2024

Limit Theorems for the Volume of Random Projections and Sections of $ℓ_{p}^{N}$ -balls

Joscha Prochno, Christoph Thaele, Philipp Tuchel

Let $B_{p}^{N}$ be the $N$ -dimensional unit ball corresponding to the $ℓ_{p}$ -norm. For each $N \in N$ we sample a uniform random subspace $E_{N}$ of fixed dimension $m\i…

cs.LG2024★ 8 cited

A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption

Marcus Rüb, Philipp Tuchel, Axel Sikora +1

A new algorithm for incremental learning in the context of Tiny Machine learning (TinyML) is presented, which is optimized for low-performance and energy efficient embedded devices…

Realising atomless laws as distance distributions on metric measure spaces

Mod-phi convergence for random variables with cyclotomic generating functions

Benchmarks in Leipzig

Large deviations for sums of multivariate stretched-exponential random variables: the few-big-jumps principle

On the Universal Representation Property of Spiking Neural Networks

Large and Moderate Deviations for Entries of Orthogonal Matrices and the Stiefel Manifold

Limit Theorems for the Volume of Random Projections and Sections of ℓpN​-balls

A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption

Limit Theorems for the Volume of Random Projections and Sections of $ℓ_{p}^{N}$ -balls