Early Stopping

Follow this topic Ask about this topic

Recent momentum

-50%

2 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

1 new paper

A weekly snapshot of new work published in Early Stopping.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Early Stopping.

Period ending 2026-09-07

1 new paper

A weekly snapshot of new work published in Early Stopping.

28 papers

Latest in Early Stopping

Browse all topics →

Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit
Sep 14, 2026Erdem KoyuncuPruning Deep Network
Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal
Sep 9, 2026Yunxiang Mo, Donghao Zhao, Hejia GengConsensus Early Stopping
Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
Aug 6, 2026Alex Buna, Shirley Xiaoqi Liu, Patrick RebeschiniEmpirical Risk Minimization Gaussian Mixture Models
Threshold-Based Early Stopping of Accumulations in Neural Networks with Binary Activation
Aug 6, 2026Quentin Luquet de Saint-Germain, Massil Ait Abdeslam, Jean Pierre DavidEarly Stopping Neural Network
Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control
Aug 5, 2026Rohit Kumar Salla, Manoj Saravanan, Simon StepputtisDiffusion Policies Early Stopping
Conformalized Rate-Adaptive Sensing
Jul 29, 2026Jiawei Yang, Yao ZhangImage Reconstruction Sensing
Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents
Jul 20, 2026Yitao Wu, Si Shen, Rui Yang +2Verifier Agent Loop
AdaStop: Cost-Aware Early Stopping for DNN Test Selection
Jul 6, 2026Bonan Shen, Wei-Jung Huang, Xin Liu +2Early Stopping Noisy Labels
When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models
Jun 29, 2026Zhe Dong, Fang Qin, Manish ShahEarly Stopping Large Reasoning Models
Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping
Jun 29, 2026Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger +2Early Stopping Stochastic
Knowing in Advance When an Evolutionary Outer Loop Will Not Help: A Pre-Registered Cheap-Baseline Screening Rule
Jun 28, 2026Ramchand KumaresanScreening Early Stopping
Halt Fast! Early Stopping for Certified Robustness
Jun 26, 2026Andrew C. Cullen, Paul Montague, Benjamin I. P. RubinsteinSmoothing Early Stopping
Semantic Early-Stopping for Iterative LLM Agent Loops
Jun 25, 2026Sahil ShrivastavaEarly Stopping Large Language Model Agents
MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling
Jun 11, 2026Wenbo Chen, Puheng Li, Mengyang Liu +2Reasoning Traces Large Models
SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction
Jun 3, 2026Kenfeng Huang, Yi Cai, Xin Wu +2Zero-Shot Inference Multi-Agent Systems
ScoreStop: Gradient-based early stopping using functional score tests
Jun 1, 2026Oliver J. Hines, Christian L. HinesEarly Stopping Gradient Boosted Tree
Cost-Aware Diffusion Draft Trees for Speculative Decoding
Jun 1, 2026Shuai Zhang, Huachuan Qiu, Hongliang He +1Speculative Decoding Diffusion Language Models
Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning
May 27, 2026Minhao Yao, Ruoyu Wang, Xihong Lin +2Early Stopping Deep Learning
FAST-ME: Foundation-aware Adaptive Stopping for Motion Estimation for Efficient IoT Video Analysis
May 22, 2026Kakia Panagidi, Stathes HadjieftymiadisMotion Estimation Early Stopping
Consolidation-Expansion Operator Mechanics:A Unified Framework for Adaptive Learning
May 11, 2026Debashis GuhaAdaptive Learning Consolidation
SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data
May 7, 2026Carlo Romeo, Girolamo Macaluso, Alessandro Sestini +1Off-Policy Evaluation Learning-Augmented Algorithms
Balancing Stability and Plasticity in Sequentially Trained Early-Exiting Neural Networks
May 6, 2026Alaa Zniber, Ouassim Karrakchou, Mounir GhoghoPlasticity Early Stopping
Adaptive Consensus in LLM Ensembles via Sequential Evidence Accumulation: Automatic Budget Identification and Calibrated Commit Signals
May 5, 2026Roberto E. MedinaEarly Stopping Confidence Calibration
TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping
Apr 22, 2026Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo +1Large Reasoning Models Early Stopping
Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles
Apr 20, 2026Emanuel Sommer, Rickmer Schulte, Sarah Deubner +2Early Stopping Markov Chain Monte Carlo
Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning
Apr 18, 2026Benteng Chen, Weida Wang, Shufei Zhang +2Large Reasoning Models Early Stopping
On Regularization via Early Stopping for Least Squares Regression
Jun 6, 2024Rishi Sonthalia, Jackie Lok, Elizaveta RebrovaKernel Ridge Regression Early Stopping
Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking
Date pendingGuangyu Chen, Boxuan Lyu, Hidetaka Kamigaito +2Neural Machine Translation Models Machine Translation

Sep 14, 2026 · cs.LGJ/K move · Enter open · S save

Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit

Erdem Koyuncu

We study compute reduction in neural networks through a unified partial versus full computation view, captured by one-shot magnitude pruning in the static regime and early exit in the adaptive regime. In an asymptotic single-neuron model, we prove a concentration theorem for one-shot magnitude pruning with explicit rates. We also introduce the conditional perceptron for early exit and show that its excess generalization error decays as a power of the compute gap, with an exponent that grows to infinity as the alignment between partial and full computations tends to one. We then extend the analysis to deep networks, characterizing how pruning-induced distortions accumulate with depth and deriving a corresponding compute-accuracy tradeoff for frozen-backbone early exit under a neural network Gaussian process model. Numerical simulations corroborate the predicted scaling laws.

Pruning Deep Network Early Stopping Response Magnitude

Open paper Ask about it PDF