No article text was recorded for this version.
non-monotonic learning curves
Version 1 of 179 papers117 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Open Problem: Monotonicity of Learning
- Blog: Minimizers of the Empirical Risk and Risk Monotonicity
- Blog: Bounds on Individual Risk for Log-loss Predictors
- Blog: The Shape of Learning Curves: a Review
- Blog: Minimizers of the Empirical Risk and Risk Monotonicity
- Blog: Also for k-means: more data does not imply better performance
- Blog: A Survey of Learning Curves with Bad Behavior: or How More Data Need Not Lead to Better Performance
- Blog: Counterintuitive Behavior of Clustering Quality: Findings for K-Means on Synthetic and Real Data
- Blog: LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought
- Blog: The Dipping Phenomenon
- Blog: Making Learners (More) Monotone
- Blog: Making Learners (More) Monotone
- Blog: Deconstructing Distributions: A Pointwise Framework of Learning
- Blog: Deep Double Descent: Where Bigger Models and More Data Hurt
- Blog: Deconstructing Distributions: A Pointwise Framework of Learning
- Blog: More Data Can Hurt for Linear Regression: Sample-wise Double Descent
- Blog: Asymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares Estimator
- Blog: Making Learners (More) Monotone
- Blog: Optimal Regularization can Mitigate Double Descent
- Blog: Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks
- Blog: Bayesian Optimization Meets Bayesian Optimal Stopping
- Blog: In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization
- Blog: The Deep Bootstrap: Good Online Learners are Good Offline Generalizers
- Blog: Risk Monotonicity in Statistical Learning
- Blog: Efficient Identification of Approximate Best Configuration of Training in Large Datasets
- Blog: Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits
- Blog: Hyperparameters Evidence and Generalisation for an Unrealisable Rule
- Blog: LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
- Blog: P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models
- Blog: MetaREVEAL: RL-based Meta-learning from Learning Curves
- Blog: AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction
- Blog: Cliff-Learning
- Blog: Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
- Blog: The Value of Out-of-Distribution Data
- Blog: Monotone Learning
- Blog: Quality vs. Quantity of Data in Contextual Decision-Making: Exact Analysis under Newsvendor Loss
- Blog: A Meta-Learning Approach to Predicting Performance and Data Requirements
- Blog: Monotone Learning
- Blog: Deep Double Descent: Where Bigger Models and More Data Hurt
- Blog: Precise Learning Curves and Higher-Order Scalings for Dot-product Kernel Regression
- Blog: Defying the gravity of learning curve: a characteristic of nearest neighbour anomaly detectors
- Blog: A Precise Performance Analysis of Support Vector Regression
- Blog: Striving for data-model efficiency: Identifying data externalities on group performance
- Blog: How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
- Blog: Optimizing Data Collection for Machine Learning
- Blog: Synthetic Dataset Acquisition for a Specific Target Domain
- Blog: Broken Neural Scaling Laws
- Blog: Power analysis for causal discovery
- Blog: Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves
- Blog: FEET: A Framework for Evaluating Embedding Techniques
- Blog: On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels
- Blog: Generalized equivalences between subsampling and ridge regularization
- Blog: Broken Neural Scaling Laws
- Blog: Optimal Ridge Regularization for Out-of-Distribution Prediction
- Blog: Selecting Near-Optimal Learners via Incremental Data Allocation
- Blog: Statistical Dynamics of Batch Learning
- Blog: Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition
- Blog: Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets
- Blog: Class-wise Generalization Error: an Information-Theoretic analysis
- Blog: Recall is the Proper Evaluation Metric for Word Segmentation
Showing 60 of 79 papers.
History & citation
Current · Permanent link
- Beyond Power Laws for Neural Scaling Prediction merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_non_monotonic_learning_curves_da3fd003,
title = {non-monotonic learning curves},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-monotonic-learning-curves/rdr_da3fd0030d3e45c68eef35256e859255},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_non_monotonic_learning_curves_da3fd003_v1,
title = {non-monotonic learning curves},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-monotonic-learning-curves/rdr_da3fd0030d3e45c68eef35256e859255/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}