No article text was recorded for this version.
short-horizon bias
Version 2 of 2115 papers159 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Understanding Short-Horizon Bias in Stochastic Meta-Optimization
- Blog: Understanding Short-Horizon Bias in Stochastic Meta-Optimization
- Blog: Discovering Temporally-Aware Reinforcement Learning Algorithms
- Blog: Learning to Optimize: A Primer and A Benchmark
- Blog: Learning Gradient Descent: Better Generalization and Longer Horizons
- Blog: Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation
- Blog: Meta-learning PINN loss functions
- Blog: To Be Greedy, or Not to Be - That Is the Question for Population Based Training Variants
- Blog: Learned Optimizers that Scale and Generalize
- Blog: Learning to Learn with Smooth Regularization
- Blog: Transferring Knowledge across Learning Processes
- Blog: Multiple-Frequencies Population-Based Training
- Blog: Glocal Hypergradient Estimation with Koopman Operator
- Blog: Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters
- Blog: Online Hyperparameter Meta-Learning with Hypergradient Distillation
- Blog: On the Implicit Bias in Deep-Learning Algorithms
- Blog: Gradient-based Hyperparameter Optimization Over Long Horizons
- Blog: Bootstrapped Meta-Learning
- Blog: Amortized Proximal Optimization
- Blog: PyLO: Towards Accessible Learned Optimizers in PyTorch
- Blog: Learning Gradient Descent: Better Generalization and Longer Horizons
- Blog: Meta-learning PINN loss functions
- Blog: MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
- Blog: Improved Adversarial Training via Learned Optimizer
- Blog: EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization
- Blog: Meta-Learning with Adjoint Methods
- Blog: Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation
- Blog: A Mathematics-Inspired Learning-to-Optimize Framework for Decentralized Optimization
- Blog: Globally Optimal On-line Learning Rules
- Blog: One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning
- Blog: Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning
- Blog: Learning by Directional Gradient Descent
- Blog: A Game of Bundle Adjustment - Learning Efficient Convergence
- Blog: On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
- Blog: Trajectory-Based Meta-Learning for Out-Of-Vocabulary Word Embedding Learning
- Blog: Understanding and correcting pathologies in the training of learned optimizers
- Blog: Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single
- Blog: Learning Large-scale Neural Fields via Context Pruned Meta-Learning
- Blog: Characterizing Implicit Bias in Terms of Optimization Geometry
- Blog: Training Stronger Baselines for Learning to Optimize
- Blog: Online Hyperparameter Meta-Learning with Hypergradient Distillation
- Blog: Adaptive Interest for Emphatic Reinforcement Learning
- Blog: Principled Acceleration of Iterative Numerical Methods Using Machine Learning
- Blog: Towards Constituting Mathematical Structures for Learning to Optimize
- Blog: Bootstrapped Meta-Learning
- Blog: Meta Learning Backpropagation And Improving It
- Blog: Discovering Evolution Strategies via Meta-Black-Box Optimization
- Blog: AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly
- Blog: Improved Adversarial Training via Learned Optimizer
- Blog: Unleash Model Potential: Bootstrapped Meta Self-supervised Learning
- Blog: Large-Scale Meta-Learning with Continual Trajectory Shifting
- Blog: Optimization as a Model for Few-Shot Learning
- Blog: Stepping on the Edge: Curvature Aware Learning Rate Tuners
- Blog: Non-greedy Gradient-based Hyperparameter Optimization Over Long Horizons
- Blog: Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies (Extended Abstract)
- Blog: Meta-Learning with Warped Gradient Descent
- Blog: Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
- Blog: Accelerating Federated Edge Learning via Optimized Probabilistic Device Scheduling
- Blog: VeLO: Training Versatile Learned Optimizers by Scaling Up
- Blog: Marthe: Scheduling the Learning Rate Via Online Hypergradients
Showing 60 of 115 papers.
History & citation
Current · Permanent link
- Scaling Learned Optimizers to Long Training Horizons merged into this direction (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_short_horizon_bias_a8fc9b9e,
title = {short-horizon bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/short-horizon-bias/rdr_a8fc9b9e76f14a948c024f26efbcf2d6},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_short_horizon_bias_a8fc9b9e_v2,
title = {short-horizon bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/short-horizon-bias/rdr_a8fc9b9e76f14a948c024f26efbcf2d6/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}