Learning to optimize has emerged as a powerful framework for various optimization and machine learning tasks. Current such "meta-optimizers" often learn in the space of continuous optimization algorithms that are point-based and uncertainty-unaware. To overcome the limitations, we propose a meta-optimizer that learns i…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
28 results for “meta-optimizer”
Careful tuning of the learning rate, or even schedules thereof, can be crucial to effective neural net training. There has been much recent interest in gradient-based meta-optimization, where one tunes hyperparameters, or even learns an optimizer, in order to minimize the expected loss when the training procedure is un…
Paper tackles robustness in adversarial noise with a meta-optimizer.
problem Sensitivity to adversarial noise hinders machine learning deployment.
method Meta-optimizer learns to robustly optimize models using adversarial examples.
result Meta-optimizer transfers adversarial knowledge to new models without generating new examples.
Memory-Augmented Meta-Optimization improves cold-start recommendation.
problem Cold-start problem in recommender systems for new users or items.
method Memory-Augmented Meta-Optimization approach with personalized and task-specific memories.
result Significant improvement in cold-start recommendation performance on multiple datasets.
Automates RL with sample-efficient hyperparameter optimization.
problem Challenges in applying deep RL due to hyperparameter sensitivity and inefficiency.
method Population-based AutoRL framework for meta-optimizing RL algorithms and architectures.
result Reduces the number of environment interactions needed for meta-optimization by up to an order of magnitude.
Self-referential meta learning avoids explicit optimization by modifying itself.
problem Dependency on human engineering in meta learning algorithms.
method Investigates self-referential meta learning systems that modify themselves without explicit optimization.
result Self-referential neural networks can improve their own modifications without explicit optimization.
Meta Optimal Transport learns from past problems to solve similar OT problems faster.
problem Solving similar optimal transport problems repeatedly from scratch is inefficient.
method Amortized optimization to predict optimal transport maps from past solutions.
result Meta OT models can solve new problems faster than standard methods.
JAX, M.D.: A Framework for Differentiable Physicsphysics.comp-ph
We introduce JAX MD, a software package for performing differentiable physics simulations with a focus on molecular dynamics. JAX MD includes a number of physics simulation environments, as well as interaction potentials and neural networks that can be integrated into these environments without writing any additional c…
SOCRATES: Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluationsstat.ML
SOCRATES uses LLMs to automate simulation optimization of complex systems.
problem Optimizing complex, expensive-to-sample stochastic systems.
method Two-stage procedure: replica construction and meta-optimization.
result Adaptive hybrid optimization schedule for real systems.
Guarantees for tuning step size using meta-gradient descent.
problem Choosing optimal parameters for optimization algorithms.
method Learning-to-learn approach with meta-gradient descent.
result Meta-gradient can explode/vanish, requiring careful meta-objective design.
Meta-theorems validate fair regression algorithms under demographic parity constraints.
problem Regression under demographic parity constraints.
method Meta-theorems and post-processing methods.
result Fair minimax optimal regression can be achieved through post-processing.
Unified RL meta-learning framework for few-shot optimization.
problem Few-shot learning optimization problems.
method Generic RL meta-learning framework that learns optimal optimization algorithms.
result Significantly improved performance on few-shot tasks.
Improves few-shot learning using multi-task representation learning theory.
problem Few-shot learning with limited data.
method Multi-task representation learning theory and spectral-based regularization.
result Improved performance of meta-learning methods through new spectral regularization.
Meta-learning is a promising method to achieve efficient training method towards deep neural net and has been attracting increases interests in recent years. But most of the current methods are still not capable to train complex neuron net model with long-time training process. In this paper, a novel second-order meta-…
Model-Agnostic Meta-Learning (MAML) and its variants have achieved success in meta-learning tasks on many datasets and settings. On the other hand, we have just started to understand and analyze how they are able to adapt fast to new tasks. For example, one popular hypothesis is that the algorithms learn good represent…
New symmetries improve meta-reinforcement learning's generalization.
problem Black-box meta reinforcement learning struggles with generalization.
method Introduce symmetries to a black-box meta RL system.
result Incorporating symmetries improves generalization to new environments.
We consider optimization problems in which the objective requires an inner loop with many steps or is the limit of a sequence of increasingly costly approximations. Meta-learning, training recurrent neural networks, and optimization of the solutions to differential equations are all examples of optimization problems wi…
Automatic Gradient Boostingstat.ML
Automatic machine learning performs predictive modeling with high performing machine learning tools without human interference. This is achieved by making machine learning applications parameter-free, i.e. only a dataset is provided while the complete model selection and model building process is handled internally thr…
Proposes GIL for semi-supervised graph classification.
problem Semi-supervised classification of graph data with limited labeled nodes.
method Graph Inference Learning framework that learns node label inference from graph topology.
result Significantly improves semi-supervised node classification performance.
Meta-Semi learns to optimize SSL with minimal hyper-parameter tuning.
problem Limited labeled data in SSL makes it impractical to tune many hyper-parameters.
method Meta-learning approach that dynamically reweights unlabeled data loss.
result Meta-Semi achieves competitive performance on various SSL tasks.
APO optimizes neural network parameters by amortizing proximal point methods.
problem Optimizing neural network parameters online and adaptively.
method APO framework that meta-learns proximal point parameters.
result APO can recover and outperform existing optimizers and schedules.
Transformers learn to solve various tasks without explicit design.
problem Training models with minimal inductive bias.
method Meta-learning approach to train general-purpose in-context learning algorithms.
result Transformers can be meta-trained to solve a wide range of tasks.
We learn a compact surrogate model for optimization problems to reduce training and inference time.
problem Solving optimization problems with unknown parameters is computationally expensive and may lead to suboptimal solutions.
method We represent the optimization problem in terms of meta-variables and learn a low-dimensional surrogate model end-to-end with the predictive model.
result We achieve a large reduction in training and inference time, and improved performance.
Meta-continual learning improves few-shot learning performance.
problem Limited applicability of deep learning solutions to real-world data.
method Unsupervised meta-continual learning with meta-optimization and self-attention.
result Meta-continual learning achieves competitive performance even without supervision.
Few-shot learning improves bearing fault diagnosis with limited data.
problem Challenges in collecting sufficient fault data for robust classifier training.
method Model-Agnostic Meta-Learning (MAML) for few-shot learning.
result Framework achieves up to 25% higher accuracy than Siamese network.
Graph neural networks (GNNs) are widely used in many applications. However, their robustness against adversarial attacks is criticized. Prior studies show that using unnoticeable modifications on graph topology or nodal features can significantly reduce the performances of GNNs. It is very challenging to design robust …
Generative model creates synthetic unlabeled data for SSL.
problem Training SSL models without real unlabeled datasets.
method Meta-optimized synthetic samples generated from generative models.
result Synthetic samples improve SSL performance more efficiently than real unlabeled data.
LSTMs show surprising few-shot learning ability, improving on MAML.
problem Few-shot learning with limited data.
method Revisited LSTM approach with Outer Product LSTM (OP-LSTM).
result OP-LSTM outperforms MAML on simple few-shot tasks, but not complex ones.