arXiv AI July 8, 2026 By Jean-Francois Bonbhel

K-ABENA: K-Adaptive Backpropagation with Error-based N-exclusion Algorithm : (Compensated Loss-Based Sample Exclusion with Unbiased Gradient Estimation)

arXiv:2607. 05903v1 Announce Type: cross Abstract: We present K-ABENA (K-Adaptive Backpropagation with Error-based N-exclusion Algorithm), a selective gradient computation framework that reduces per-iteration training cost by excluding a fraction of low-loss ("minor") observations from the backward pass.

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

safety

arXiv Machine Learning

Jun 9

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning

arXiv:2602. 02431v2 Announce Type: replace-cross Abstract: It is folklore that reusing training data more than once can improve the statistical efficiency of gradient-based learning.

By Filip Kova\v{c}evi\'c, Hong Chang Ji, Denny Wu, Mahdi Soltanolkotabi, Marco Mondelli

arXiv Machine Learning

Jul 14

Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization

arXiv:2607. 10618v1 Announce Type: cross Abstract: We consider the recovery of a pair of sparse vectors from a limited number of nonlinear observations of their superposition: $y_i=g(\inner{\ba_i}{\bPhi\bw^\ast+\bPsi\bz^\ast})+e_i$, $i=1,\dots,m$, with $m\ll n$, incoherent orthonormal bases $\bPhi,\bPsi$, a scalar link $g$, and noise $e_i$ that may be heavy-tailed or contaminated.

By Raziyeh Takbiri

agents efficiency safety

arXiv Machine Learning

Jul 14

Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective

arXiv:2607. 11146v1 Announce Type: new Abstract: We study the coupled objective J_K^WOR = E_{S ~ PL-WOR_K}[max_{i in S} R_i]: the expected maximum reward of a size-K Plackett-Luce draw without replacement, the law of Gumbel-Top-K / Stochastic Beam Search decoding.

By Melveena Jolly, Midhun Xavier

arXiv Machine Learning

6d ago

A New First-Order Meta-Learning Algorithm with Convergence Guarantees

arXiv:2409. 03682v2 Announce Type: replace Abstract: Learning new tasks by leveraging prior experience is a fundamental trait of intelligent systems.

By El Mahdi Chayti, Martin Jaggi

llms efficiency safety

arXiv Machine Learning

Jul 17

Adaptive Runge-Kutta Step Control Buys Training Loss, Not Generalization: An Honest Compute-Matched Study of RK-Adam Optimizers

arXiv:2607. 14516v1 Announce Type: new Abstract: Interpreting optimizers as gradient-flow discretizations has motivated applying higher-order Runge-Kutta (RK) integrators to neural networks.

By Akhilesh Gogikar

arXiv Machine Learning

Jun 4

On the Relationship Between CoCoA and ADMM for Distributed Empirical Risk Minimization

arXiv:2502. 00470v3 Announce Type: replace-cross Abstract: Distributed empirical risk minimization (ERM) is often studied through two influential yet seemingly separate families of methods: CoCoA-type algorithms, derived from distributed dual coordinate ascent, and ADMM-type algorithms, derived from consensus and proximal splitting.

By Runxiong Wu, Andi Wang

Related stories

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning

Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization

Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective

A New First-Order Meta-Learning Algorithm with Convergence Guarantees

Adaptive Runge-Kutta Step Control Buys Training Loss, Not Generalization: An Honest Compute-Matched Study of RK-Adam Optimizers

On the Relationship Between CoCoA and ADMM for Distributed Empirical Risk Minimization