José I. Mestre

Enrique S. Quitana-Ortí

CoRR, May, 2026

StableGrad: Backward Scale Control without Batch Normalization.

[BibT_eX]

[DOI]

CoRR, May, 2026

FedOUI: OUI-Guided Client Weighting for Federated Aggregation.

[BibT_eX]

[DOI]

CoRR, May, 2026

OUI as a Structural Observable: Towards an Activation-Centric View of Neural Network Training.

[BibT_eX]

[DOI]

CoRR, May, 2026

OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns.

[BibT_eX]

[DOI]

CoRR, May, 2026

Refresh-Scaling the Memory of Balanced Adam.

[BibT_eX]

[DOI]

CoRR, May, 2026

FedSQ: Optimized Weight Averaging via Fixed Gating.

[BibT_eX]

[DOI]

CoRR, April, 2026

λ-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks.

[BibT_eX]

[DOI]

CoRR, March, 2026

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic.

[BibT_eX]

[DOI]

CoRR, March, 2026

Regime Change Hypothesis: Foundations for Decoupled Dynamics in Neural Network Training.

[BibT_eX]

[DOI]

CoRR, February, 2026

Why Adam Works Better with β<sub>1</sub> = β<sub>2</sub>: The Missing Gradient Scale Invariance Principle.

[BibT_eX]

[DOI]

CoRR, January, 2026

2025

GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling.

[BibT_eX]

[DOI]

CoRR, October, 2025

Latency-Critical Quantized Inference With Transformer Decoders on ARM and RISC-V CPUs.

[BibT_eX]

[DOI]

IEEE Internet Things J., July, 2025

Sinusoidal Initialization, Time for a New Start.

[BibT_eX]

[DOI]

CoRR, May, 2025

OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection.

[BibT_eX]

[DOI]

CoRR, April, 2025

Deep learning inference optimisation for IoT: Conv2D-ReLU-BN layer fusion and quantisation.

[BibT_eX]

[DOI]

J. Supercomput., March, 2025

Decoupling Structural and Quantitative Knowledge in ReLU-based Deep Neural Networks.

[BibT_eX]

[DOI]

José Cano

Proceedings of the 5th Workshop on Machine Learning and Systems, 2025

2023

Using machine learning to model the training scalability of convolutional neural networks on clusters of GPUs.

[BibT_eX]

[DOI]

Computing, May, 2023

GreenLightningAI: An Efficient AI System with Decoupled Structural and Quantitative Knowledge.

[BibT_eX]

[DOI]

CoRR, 2023

2021

PyDTNN: A user-friendly and extensible framework for distributed deep learning.

[BibT_eX]

[DOI]

J. Supercomput., 2021

Evaluation of MPI Allreduce for Distributed Training of Convolutional Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 29th Euromicro International Conference on Parallel, 2021

Performance Modeling for Distributed Training of Convolutional Neural Networks.

[BibT_eX]

[DOI]