Improves sample efficiency in evolutionary policy search methods.
problem Worse sample efficiency in evolutionary policy search methods.
method Importance mixing to reuse more samples.
result Improves sample efficiency but still less than deep reinforcement learning.
Combines evolutionary and RL methods for better policy search.
problem Low sample efficiency in evolutionary methods and high sensitivity in RL methods.
method Combines CEM and td3 algorithms for policy search.
result cem-rl offers a better trade-off between performance and sample efficiency.
Evolutionary Strategies optimize hyper-parameters for off-policy learning.
problem Hyper-parameter sensitivity in off-policy learning.
method Application of Evolutionary Strategies for online hyper-parameter tuning.
result Our method outperforms state-of-the-art baselines.
Robotic table tennis learns efficient policies to return balls at 100Hz.
problem Developing efficient robotic table tennis strategies.
method Model-free reinforcement learning using evolutionary search on CNN-based policies.
result Robots can develop multi-modal styles (forehand and backhand) with 80% return rate.
Evo-NAS combines neural and evolutionary methods for efficient neural architecture search.
problem Efficiently searching for optimal neural architectures in deep learning.
method Evolutionary-Neural hybrid agents that combine the strengths of neural and evolutionary algorithms.
result Evo-NAS outperforms both neural and evolutionary agents in architecture search for various classification tasks.
Early stopping method saves up to 75% computation time in policy search tasks.
problem Lengthy evaluation times in optimization problems, especially in robotics.
method A generalized early stopping criterion that only uses objective value at each time step.
result The method saves up to 75% computation time compared to no stopping.
Improves neural network search in combinatorial spaces of mathematical symbols.
problem Early commitment and initialization bias limit exploration in neural network search.
method Entropy regularization and distribution initialization methods.
result Improves performance, increases sample efficiency, lowers solution complexity.
Paper uses CMAB to improve NAS efficiency and accuracy.
problem Improving efficiency and accuracy of NAS for DNNs.
method Formulated NAS as CMAB, used Nested Monte-Carlo Search.
result Discovered cell structure achieves comparable accuracy to state-of-the-art, 20x faster.
A real-time federated neural architecture search approach reduces costs and improves performance.
problem High communication and computational demands in federated learning for large models.
method Evolutionary approach with double-sampling technique to optimize model performance and reduce costs.
result Effective real-time federated neural architecture search for deep models on edge devices.
AutoRL automates reward tuning for RL, improving performance on complex tasks.
problem Suboptimal policies when using direct rewards in RL.
method Evolutionary search over RL agents to find optimal rewards.
result Improves RL performance on complex tasks.
EA-LSTM improves LSTM for time series prediction by evolving attention.
problem LSTMs struggle with assigning varying attention to sub-windows in time series data.
method Evolutionary attention-based LSTM with competitive random search.
result EA-LSTM achieves competitive performance in multivariate time series prediction.
Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the true gradient) is available instead. This arises when an approximate gradient is easier to compute t…
EvoNUDGE uses graph neural networks to improve genetic programming performance.
problem Efficiency in evolutionary computation for problem solving.
method Graph neural network to elicit additional knowledge from symbolic regression problems.
result EvoNUDGE significantly outperforms conventional and neural genetic programming methods.
New IT representation improves symbolic regression approximations.
problem Finding better approximations to real-world data sets.
method Evolutionary Algorithm with IT representation using only mutation.
result IT representation finds better approximations than traditional methods.
NPENAS improves neural architecture search efficiency and accuracy.
problem Efficient and accurate neural architecture search (NAS) for minimizing search costs.
method Proposes NPENAS, a neural predictor guided evolutionary algorithm that enhances exploration ability of evolutionary algorithms.
result NPENAS-BO and NPENAS-NP outperform existing NAS algorithms on NASBench-201, NASBench-101, and DARTS.
Evolutionary algorithms improve neural network performance by discovering better activation functions.
problem The choice of activation function affects neural network performance, but ReLU remains dominant.
method Defined a tree-based search space of candidate activation functions and used evolutionary algorithms (mutation, crossover, exhaustive search) to explore and discover better functions.
result Replacing ReLU with evolved activation functions statistically significantly increases network accuracy.
BoGA combines evolutionary search with Bayesian optimization for efficient protein design.
problem Designing novel proteins with specific characteristics is challenging due to sequence space complexity.
method BoGA integrates a genetic algorithm with Bayesian optimization to efficiently explore sequence space.
result BoGA accelerates discovery of high-confidence binders for diverse protein design objectives.
A graph-based evolutionary algorithm automates machine learning workflows.
problem Automated machine learning to reduce manual operations.
method Graph-based architecture for flexible model combinations, evolutionary algorithm with mutation and heredity operators, Bayesian hyper-parameter optimization.
result State-of-the-art performance compared to other AutoML systems.
MERL uses evolutionary and gradient-based methods to optimize sparse team-based and dense agent-specific rewards in multiagent coordination.
problem Training multiagent reinforcement learning policies on sparse team-based rewards is difficult and relying solely on agent-specific rewards is sub-optimal.
method MERL employs a split-level training platform with an evolutionary algorithm and a gradient-based optimizer, transferring skills between the two processes.
result MERL significantly outperforms state-of-the-art methods on coordination benchmarks.
This paper optimizes search experiences in two-sided marketplaces by balancing multiple conflicting metrics.
problem Balancing conflicting business metrics in two-sided marketplaces like eBay and Etsy.
method Joint optimization of market-level metrics using Evolutionary Strategies.
result Demonstrated effectiveness of the proposed method on Etsy data.
ESPD improves learning efficiency in sparse reward reinforcement learning.
problem Sparse reward reinforcement learning challenges.
method Evolutionary Stochastic Policy Distillation (ESPD) based on drifted random walk insight.
result High learning efficiency demonstrated in MuJoCo robotics control suite experiments.
EFS uses LLMs to optimize sparse portfolios by evolving alpha factors.
problem Sparse portfolio optimization in dynamic market regimes.
method Evolutionary feedback loop with LLM-generated alpha factors.
result Significantly outperforms baselines in diverse datasets.
OpEvo automates tensor operator optimization for better efficiency.
problem Manual optimization of tensor operators is inefficient and limited.
method OpEvo uses evolutionary computation with topology-aware mutation.
result OpEvo finds optimal configurations with less effort and variance.
BS-NAS broadens and shrinks search space for optimal neural architectures.
problem Suboptimal channel numbers and model averaging effects in One-Shot NAS methods.
method Broadening with spring block for channel search, shrinking with underperforming operations removal, evolutionary algorithm for optimal architecture search.
result BS-NAS achieves state-of-the-art performance on ImageNet.
FairNAS improves fairness in neural architecture search evaluation.
problem Improving accuracy of model ranking in neural architecture search.
method Proposes expectation and strict fairness constraints to ensure equal optimization opportunities for all blocks.
result Demonstrates improved model ranking and accuracy with FairNAS-A.
Survey of neural architecture search methods.
problem Automating the selection of neural network architectures.
method Comprehensive analysis of existing methods using reinforcement learning, evolutionary algorithms, and surrogate models.
result Unified formalism for categorizing and comparing architecture search methods.
HMCNAS generates competitive neural architectures without human-defined parameters.
problem Lack of human-defined parameters in Neural Architecture Search.
method Combines Hidden Markov Chains and Bayesian Optimization for autonomous search space generation and competitive model generation.
result HMCNAS generates competitive models in a short time without human-defined parameters.
Algorithm combines RL and black-box optimization for policy learning.
problem Improving policy learning efficiency in RL.
method Combines actor-critic approach with stochastic search and parametric/local policy estimation.
result Demonstrates effectiveness on diverse RL tasks with limited compute.
AutoAlpha efficiently discovers effective alpha factors for quantitative investment.
problem Mining effective alpha factors for successful quantitative investment models.
method Hierarchical evolutionary algorithm with PCA-QD search, warm start, and replacement methods.
result AutoAlpha discovers and generates effective formulaic alphas for portfolio optimization.
VisEvol uses evolutionary optimization to find optimal hyperparameters for machine learning models.
problem Finding the best hyperparameters for complex machine learning models is computationally intensive and challenging.
method VisEvol employs evolutionary optimization, storing performant models and improving others through crossover and mutation processes.
result VisEvol generates a voting ensemble of models with improved predictive performance.
New method speeds up image denoising models without sacrificing performance.
problem Efficiently training models for image denoising tasks.
method Introduces superkernel techniques for fast training of dense prediction models.
result Demonstrates effectiveness on SIDD+ benchmark with 6-8 RTX2080 GPU hours.
Quality-Diversity algorithms explore multiple high-performing solutions in a search space.
problem Finding multiple high-performing solutions in complex optimization problems.
method Evolutionary computation approach focusing on behavioral space and holistic solution distribution.
result Quality-Diversity algorithms provide a comprehensive view of high-performing solutions in a search space.
DONNA rapidly finds optimal neural networks across diverse spaces.
problem Efficient scaling and handling of diverse architectural search-spaces in NAS.
method Three-phase pipeline: accuracy predictor, rapid evolutionary search, and optimal model finetuning.
result 100x faster than MNasNet in finding state-of-the-art architectures on-device.
Guided Evolution improves NAS efficiency and accuracy.
problem NAS methods converge to local minima and are complex.
method G-EA: guided evolutionary approach with initialization evaluation and continuous knowledge extraction.
result G-EA achieves state-of-the-art results in CIFAR-10, CIFAR-100, and ImageNet16-120.
SDE automatically recovers interpretable discrete distributions.
problem Limited interpretable discrete probability laws.
method Unsupervised framework using symbolic density estimation.
result Accurately recovers interpretable discrete distributions.
DO uses DNNs to solve combinatorial optimisation problems.
problem Solving complex combinatorial optimisation problems.
method Combines evolutionary search with DNNs to learn and exploit problem structure.
result DO can solve problems like HTOP and MCparity that other algorithms cannot.
This paper reviews hyperparameter optimization methods and best practices.
problem Finding optimal hyperparameters for machine learning models.
method Various hyperparameter optimization methods are reviewed, including grid search, random search, evolutionary algorithms, Bayesian optimization, Hyperband, and racing.
result Practical recommendations for conducting hyperparameter optimization are provided.
PGS uses neural networks to improve policies online without search trees.
problem Limited scalability of Monte Carlo Tree Search (MCTS) for high branching factor games.
method Adapts a neural network simulation policy via policy gradient updates, avoiding search trees.
result PGS achieves comparable performance to MCTS and defeats strong Hex agents.
Test the robustness of quantum-enhanced phase estimation under various noise conditions.
problem Evaluate the robustness of quantum-enhanced adaptive phase estimation (QEAPE) in noisy conditions.
method Simulated QEAPE under four phase-noise models and compared resource usage of evolutionary and Bayesian control policies.
result Demonstrated the effectiveness of both evolutionary and Bayesian control policies in noisy conditions.
Ansor generates high-performance tensor programs for deep learning.
problem Generating high-performance tensor programs for deep learning on various hardware platforms is challenging.
method Ansor uses a hierarchical representation of the search space, sampling programs, and evolutionary search with a learned cost model to find high-performance programs.
result Ansor improves deep neural network execution performance up to 3.8x on Intel CPU, 2.6x on ARM CPU, and 1.7x on NVIDIA GPU.
Evolved Transformer improves on Transformer architecture for language tasks.
problem Improving Transformer architecture for sequence tasks.
method Evolutionary architecture search with warm starting and dynamic resource allocation.
result Evolved Transformer achieves state-of-the-art BLEU scores and reduces parameter count.
EA improves clustering efficiency using crossover and mutation.
problem Efficiently clustering data using model-based methods.
method Developed an evolutionary algorithm with crossover and mutation for model-based clustering.
result EA outperforms EM algorithm and k-means in clustering performance.
In this paper we present an evolutionary optimization approach to solve the risk parity portfolio selection problem. While there exist convex optimization approaches to solve this problem when long-only portfolios are considered, the optimization problem becomes non-trivial in the long-short case. To solve this problem…
We present a model of an economy inspired by individual based model approaches in evolutionary ecology. We demonstrate that evolutionary dynamics in a space of companies interconnected through a correlated interaction matrix produces time dependencies of the total size of the economy total number of companies, companie…
The study examines how permutation-based optimization performance varies across different function representations.
problem Understanding how the order of function evaluations affects optimization performance.
method Iterative search setting with sampling without replacement, algebraic function recombination, correlation analysis, hierarchical clustering, PCA, ANOVA.
result Algebraically modified benchmarks yield stable re-rankings and coherent clusters of functions and sampling policies, indicating non-additive search effort.
Novel evolutionary strategy solves stochastic constrained optimization problems.
problem Optimizing objective functions with stochastic constraints in reinforcement learning.
method Design of a novel optimization algorithm with a sufficient decrease mechanism for stochastic constrained problems.
result Demonstrated convergence of the algorithm on control tasks and constrained optimization problems.
Optimizes sampling in continuous domains by adjusting search distribution.
problem Improving sampling efficiency in continuous domains.
method Analyzes and refines the search distribution based on population size and dimension.
result Explicit values for reshaping the search distribution are provided.
Trust-region methods and natural gradients are equivalent in certain policy search scenarios.
problem Improving policy search methods in continuous control tasks.
method Introducing compatible policy search (COPOS) that uses natural parameterization and compatible value function approximation to control entropy loss.
result COPOS yields state-of-the-art results in challenging tasks and reduces entropy loss.