arXiv Machine Learning August 14, 2026 By Farhang Yeganegi, Arian Eamaz, Mojtaba Soltanalian

Training Under Challenge: Executable Certificates and Challenge-Closed Optimality for Neural Networks

Read the original on arXiv Machine Learning →

arXiv:2608. 12655v1 Announce Type: new Abstract: A flat training curve does not reveal whether a neural network has reached a global optimum, is locally trapped, is representation-limited, or is mismatched to its trainer.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

efficiency

arXiv AI

Jul 1

Improving Certified Robustness via Adversarial Distillation

arXiv:2606. 31653v1 Announce Type: cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set.

By Matteo Melis, Jesus Martinez Del Rincon, Vishal Sharma

efficiency benchmarks safety

arXiv Machine Learning

Jun 2

Multigrade Neural Network Approximation

arXiv:2601. 16884v3 Announce Type: replace Abstract: We study multigrade deep learning (MGDL) as a principled framework for structured error refinement in deep neural networks.

By Shijun Zhang, Zuowei Shen, Yuesheng Xu

arXiv Machine Learning

Jul 9

Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance

arXiv:2607. 07665v1 Announce Type: new Abstract: Classifier-free guidance (CFG) is the standard way to strengthen class-conditioning in diffusion and flow-matching samplers, yet at large guidance it oversaturates and destabilizes, symptoms practitioners suppress with more steps or limited-interval schedules.

By Shiheng Zhang

diffusion

arXiv Machine Learning

Jul 10

Closing the Null Space: Guidance-Aware Quantization for Classifier-Free Diffusion

arXiv:2607. 08241v1 Announce Type: cross Abstract: Deploying classifier-free guidance (CFG) diffusion models under real-world compute budgets requires quantization, yet existing post-training quantization (PTQ) methods treat CFG models as single-branch networks, ignoring the paired conditional/unconditional structure that CFG inference fundamentally relies on.

By Abdullah Al Shafi, Sumaiya Rahim Suma

diffusion efficiency

arXiv Machine Learning

Jun 5

Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss

arXiv:2606. 06418v1 Announce Type: new Abstract: Many modern applications of deep learning involve training a neural network via a one-step prediction loss (e.

By Thomas T. Zhang, Alok Shah, Yifei Zhang, Vincent Zhang, Nikolai Matni, Max Simchowitz

robotics

arXiv AI

Jul 29

CIFNet: An Analytic Neural Learning Framework for Efficient and Calibrated Class-Incremental Learning

arXiv:2509. 11285v2 Announce Type: replace-cross Abstract: Class-Incremental Learning (CIL) in deep neural networks is conventionally framed as an iterative gradient-based optimization problem, incurring high computational cost, hyperparameter sensitivity, and risk of catastrophic forgetting.

By Alejandro Dopico-Castro, Oscar Fontenla-Romero, Bertha Guijarro-Berdi\~nas, Amparo Alonso-Betanzos

rag diffusion safety

Related stories

Improving Certified Robustness via Adversarial Distillation

Multigrade Neural Network Approximation

Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance

Closing the Null Space: Guidance-Aware Quantization for Classifier-Free Diffusion

Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss

CIFNet: An Analytic Neural Learning Framework for Efficient and Calibrated Class-Incremental Learning