Cover Image

Training Memory in Deep Neural Networks: Mechanisms, Evidence, and Measurement Gaps

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sevetlidis, Vasileios, Pavlidis, George
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability
by: Sevetlidis, Vasileios, et al.
Published: (2026)

Gauge-invariant representation holonomy
by: Sevetlidis, Vasileios, et al.
Published: (2026)

Angular Regularization for Positive-Unlabeled Learning on the Hypersphere
by: Sevetlidis, Vasileios, et al.
Published: (2025)

Dens-PU: PU Learning with Density-Based Positive Labeled Augmentation
by: Sevetlidis, Vasileios, et al.
Published: (2023)

A Fiber Criterion for Representation Identifiability in Supervised Learning
by: Sevetlidis, Vasileios
Published: (2026)

Defect detection using weakly supervised learning
by: Sevetlidis, Vasileios, et al.
Published: (2023)

Deep Neural Networks with 3D Point Clouds for Empirical Friction Measurements in Hydrodynamic Flood Models
by: Haces-Garcia, Francisco, et al.
Published: (2024)

Armada: Memory-Efficient Distributed Training of Large-Scale Graph Neural Networks
by: Waleffe, Roger, et al.
Published: (2025)

Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting
by: Shu, Yuxuan, et al.
Published: (2025)

Evaluation of Bio-Inspired Models under Different Learning Settings For Energy Efficiency in Network Traffic Prediction
by: Tsiolakis, Theodoros, et al.
Published: (2024)

On the Hardness of Training Deep Neural Networks Discretely
by: Doron-Arad, Ilan
Published: (2024)

Inverted Activations: Reducing Memory Footprint in Neural Network Training
by: Novikov, Georgii, et al.
Published: (2024)

Memory Faults in Activation-sparse Quantized Deep Neural Networks: Analysis and Mitigation using Sharpness-aware Training
by: Malhotra, Akul, et al.
Published: (2024)

On Measuring Intrinsic Causal Attributions in Deep Neural Networks
by: Saha, Saptarshi, et al.
Published: (2025)

Training Deep Morphological Neural Networks as Universal Approximators
by: Fotopoulos, Konstantinos, et al.
Published: (2025)

Concurrent Training and Layer Pruning of Deep Neural Networks
by: Guenter, Valentin Frank Ingmar, et al.
Published: (2024)

Bulk-Switching Memristor-based Compute-In-Memory Module for Deep Neural Network Training
by: Wu, Yuting, et al.
Published: (2023)

Advancing Physics Data Analysis through Machine Learning and Physics-Informed Neural Networks
by: Vatellis, Vasileios
Published: (2024)

Exact Gauss-Newton Optimization for Training Deep Neural Networks
by: Korbit, Mikalai, et al.
Published: (2024)

Deep Neural Network Training as Random Effects: An Optimization-Inference Duality
by: Yao, Minhao, et al.
Published: (2026)

Solving Inverse Problems with Deep Linear Neural Networks: Global Convergence Guarantees for Gradient Descent with Weight Decay
by: Laus, Hannah, et al.
Published: (2025)

CPT: Efficient Deep Neural Network Training via Cyclic Precision
by: Fu, Yonggan, et al.
Published: (2021)

Complexity-Aware Training of Deep Neural Networks for Optimal Structure Discovery
by: Guenter, Valentin Frank Ingmar, et al.
Published: (2024)

TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training
by: Loeschcke, Sebastian, et al.
Published: (2025)

GPU Memory Usage Optimization for Backward Propagation in Deep Network Training
by: Hong, Ding-Yong, et al.
Published: (2025)

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
by: Hao, Yongchang, et al.
Published: (2024)

Benchmarking Neural Network Training Algorithms
by: Dahl, George E., et al.
Published: (2023)

Convolutional Neural Networks for Accurate Measurement of Train Speed
by: Tian, Haitao, et al.
Published: (2025)

Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
by: Xue, Anton, et al.
Published: (2022)

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
by: Huang, Kezhao, et al.
Published: (2023)

Theory-to-Practice Gap for Neural Networks and Neural Operators
by: Grohs, Philipp, et al.
Published: (2025)

Layerwise Progressive Freezing Enables STE-Free Training of Deep Binary Neural Networks
by: Smith, Evan Gibson, et al.
Published: (2026)

Memory Analysis on the Training Course of DeepSeek Models
by: Zhang, Ping, et al.
Published: (2025)

PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Time
by: Pourali, Alireza, et al.
Published: (2024)

SortedNet: A Scalable and Generalized Framework for Training Modular Deep Neural Networks
by: Valipour, Mojtaba, et al.
Published: (2023)

AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
by: Tenison, Irene, et al.
Published: (2025)

Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks
by: Njungle, Nges Brian, et al.
Published: (2026)

On the Dataless Training of Neural Networks
by: Velasquez, Alvaro, et al.
Published: (2025)

Using the IBM Analog In-Memory Hardware Acceleration Kit for Neural Network Training and Inference
by: Gallo, Manuel Le, et al.
Published: (2023)

Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks
by: Cho, Wonyong, et al.
Published: (2026)