arXiv subjects

Maria Matveev

Publications and source records attributed to Maria Matveev.

4 recordsLinked to original sources

arXiv2026

Functional Degeneracy in Neural Networks: Measurement and Pruning

A central question in modern machine learning is how much a trained model can be compressed without changing its behavior, to reduce the memory, compute and energy required to deploy it. To study this, we quantify functional degeneracy through the behavioral recovery rank, defined as the number of leading behavioral-Hessian eigendirections required to recover a trained model's performance. Using the behavioral recovery rank as a geometric benchmark for compression, we find that structural and magnitude pruning retain more degrees of freedom, even after the task is saturated. This gap suggests that functional redundancy is distributed across parameter directions and is not exposed by individual weights or neurons.

cs.LG↗

arXiv2026

Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining

Large language models exhibit impressive cross-lingual capabilities. However, prior work analyzes this phenomenon through isolated factors and at sparse points during training, limiting our understanding of how cross-lingual generalization emerges--particularly in the early phases of learning. To study the early trajectory of linguistic and translation capabilities, we pretrain a multilingual 1.7B model on nine diverse languages, capturing checkpoints at a much finer granularity. We use word-level translation as a testbed, introducing a novel dataset to trace how translation develops over training through behavioral analyses, model-component analysis, and parameter-based ablations. We find that the model quickly acquires basic linguistic capabilities in parallel with token-level copying, while translation develops in two distinct phases: an initial phase dominated by copying and surface-level similarities, and a second phase in which more generalizing translation mechanisms are developed while copying is refined. Together, these findings provide a fine-grained view of how cross-lingual generalization develops during multilingual pretraining.

cs.CL↗

arXiv2025

Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization

The remarkable generalization properties of overparameterized networks are often attributed to implicit biases, such as norm minimization at small learning rates and low sharpness in the Edge-of-Stability regime. In this work, we argue that a comprehensive understanding of the generalization performance of gradient descent requires analyzing the interaction between these various forms of implicit regularization. We empirically demonstrate that the learning rate interpolates between low parameter norm and low sharpness of the trained model. We furthermore prove that neither implicit bias alone minimizes the generalization error for diagonal linear networks trained on a simple regression task. These findings demonstrate that focusing on a single implicit bias is insufficient to explain good generalization, and they motivate a broader view of implicit regularization that captures the dynamic trade-off between norm and sharpness induced by non-negligible learning rates.

cs.LG↗

arXiv2025

ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior

Post-hoc interpretability methods typically attribute a model's behavior to its components, data, or training trajectory in isolation, and are often tied to a particular level of granularity along the local-to-global spectrum. This leads to explanations that lack a unified view and may miss key interactions. We present ExPLAIND, a theoretically grounded, unified framework that integrates model components, data, and training trajectory while supporting explanations across granularities. We generalize recent work on gradient path kernels, reformulating models trained by AdamW as kernel machines. From the resulting kernel feature maps, we derive novel parameter-wise and step-wise influence scores. We empirically validate the resulting decomposition of model behavior in several settings and apply ExPLAIND to two case studies. Our findings on a Transformer exhibiting Grokking support previously proposed learning phases, while refining the final phase as one in which outer layers align around a representation pipeline learned after memorization. For EuroLLM pretraining, ExPLAIND reveals a two-phase dynamic, with the first characterized by outer-layer MLP learning and the second by increased relative influence of intermediate attention layers. These results establish ExPLAIND as a unified framework for interpreting model behavior and training dynamics.

cs.LG↗