6 papers
Uniform Estimation and Inference for Nonparametric Partitioning-Based M-Estimators
Matias D. Cattaneo, Yingjie Feng, Boris Shigida
This paper presents uniform estimation and inference theory for a large class of nonparametric partitioning-based M-estimators. The main theoretical results include: (i) uniform co…
When Independent Sampling Outperforms Agentic Reasoning
Yihe Dong, Boris Shigida
We study how to allocate inference-time compute for competitive programming under fixed budgets. Evaluating 216 Codeforces problems across Divisions 1-3, we compare agent-based rea…
The Effect of Mini-Batch Noise on the Implicit Bias of Adam
Matias D. Cattaneo, Boris Shigida
With limited high-quality data and growing compute, multi-epoch training is gaining back its importance across sub-areas of deep learning. Adam(W), versions of which are go-to opti…
Learning Rate Transfer in Normalized Transformers
Boris Shigida, Boris Hanin, Andrey Gromov
The Normalized Transformer, or nGPT (arXiv:2410.01131) achieves impressive training speedups and does not require weight decay or learning rate warmup. However, despite having hype…
How Memory in Optimization Algorithms Implicitly Modifies the Loss
Matias D. Cattaneo, Boris Shigida
In modern optimization methods used in deep learning, each update depends on the history of previous iterations, often referred to as memory, and this dependence decays fast as the…
Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
Matias D. Cattaneo, Boris Shigida
We analyze gradient descent with Polyak heavy-ball momentum (HB) whose fixed momentum parameter provides exponential decay of memory. Building on Kovachki and Stuart…