3 papers
cs.LG2026
Removing spurious minima for planar features by skip connections
Jakob Paul Zimmermann, Moritz Grillo, Andrei Balakin +1
Understanding loss landscapes is central to explaining neural-network training, yet their structure remains only partially understood even in simple models. We study the Gaussian p…
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.CO2025
Maxout Polytopes
Andrei Balakin, Shelby Cox, Georg Loho +1
Maxout polytopes are defined by feedforward neural networks with maxout activation function and non-negative weights after the first layer. We characterize the parameter spaces and…