activity
20242026
collaborators

11 papers

cs.LG2026

Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining

Yunwei Ren, Yatin Dandi, Florent Krzakala +1

The empirical success of deep learning is often attributed to deep networks' ability to exploit hierarchical structure in data, constructing increasingly complex features across la…

stat.ML2026

Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model

Arie Wortsman-Zurich, Hugo Tabanelli, Yatin Dandi +2

We propose a simple mechanism by which scaling laws emerge from feature learning in multi-layer networks. We study a high-dimensional hierarchical target that is a globally high-de…

cond-mat.dis-nn2026

Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method

Yatin Dandi, David Gamarnik, Francisco Pernice +1

Dynamical Mean Field Theory (DMFT) provides an asymptotic description of the dynamics of macroscopic observables in certain disordered systems. Originally pioneered in the context…

stat.ML2026

Deep Learning of Compositional Targets with Hierarchical Spectral Methods

Hugo Tabanelli, Yatin Dandi, Luca Pesce +1

Why depth yields a genuine computational advantage over shallow methods remains a central open question in learning theory. We study this question in a controlled high-dimensional…

math.CO2026

Minimum Number of Monochromatic Subgraphs of a Random Graph

Yatin Dandi, David Gamarnik, Haodong Zhu

We consider the problem of minimizing the number of monochromatic subgraphs of a random graph, when each node of the host graph is assigned one of the two colors. Using a recently…

stat.ML2026

Asymptotics of Non-Convex Generalized Linear Models in High-Dimensions: A proof of the replica formula

Matteo Vilucchio, Yatin Dandi, Matéo Pirio Rossignol +2

The analytic characterization of the high-dimensional behavior of optimization for Generalized Linear Models (GLMs) with Gaussian data has been a central focus in statistics and pr…