Novel neural computer learns algorithmic solutions for symbolic tasks.
problem Learning abstract strategies for unfamiliar problems.
method Memory-augmented neural network architecture with Evolution Strategies.
result Strong generalization and abstraction across various tasks.
Combines NES and PPO to enhance exploration in various environments.
problem Improving exploration in reinforcement learning environments.
method Parameter transfer and parameter space noise methods for combining NES and PPO.
result PPO benefits from both NES methods in discrete and continuous control tasks.
Stochastic neural net weights are used in a variety of contexts, including regularization, Bayesian neural nets, exploration in reinforcement learning, and evolution strategies. Unfortunately, due to the large number of weights, all the examples in a mini-batch typically share the same weight perturbation, thereby limi…
We propose a population-based Evolutionary Stochastic Gradient Descent (ESGD) framework for optimizing deep neural networks. ESGD combines SGD and gradient-free evolutionary algorithms as complementary algorithms in one framework in which the optimization alternates between the SGD step and evolution step to improve th…
ES-Single uses ES to estimate gradients in unrolled graphs, reducing variance and improving performance.
problem Estimating gradients in unrolled computation graphs with low variance and stability.
method Evolution strategies (ES) applied to unrolled graphs, with a single perturbation per particle.
result ES-Single reduces variance compared to PES, leading to better performance in various tasks.
ES and FD gradients converge as optimization dimension grows.
problem Understanding the relationship between Evolution Strategies and Finite Differences gradients.
method Analyzing the convergence of gradients as the optimization dimension increases.
result ES and FD gradients converge as the dimension of the vector under optimization increases.
ADNN uses prior knowledge to construct financial features.
problem Feature construction in financial trading.
method Tailored neural network structure with domain knowledge.
result ADNN constructs more informative features than genetic programming.
In the brain, learning signals change over time and synaptic location, and are applied based on the learning history at the synapse, in the complex process of neuromodulation. Learning in artificial neural networks, on the other hand, is shaped by hyper-parameters set before learning starts, which remain static through…
PES method reduces bias in gradient estimation for unrolled graphs.
problem High variance and bias in gradient estimation for unrolled computation graphs.
method Divide graph into unrolls, apply ES update, accumulate correction terms.
result PES provides unbiased, low-variance gradient estimates.
With the breakthrough of computational power and deep neural networks, many areas that we haven't explore with various techniques that was researched rigorously in past is feasible. In this paper, we will walk through possible concepts to achieve robo-like trading or advising. In order to accomplish similar level of pe…
Deep learning approximates PDE evolution operators from solution data.
problem Recovering unknown time-dependent PDEs from solution data.
method Approximate evolution operator in modal space, train deep neural network.
result Deep learning method accurately approximates PDE solutions.
New method for portfolio management learns from past wealth evolution.
problem Optimizing portfolio selection based on past performance.
method Simulated annealing clustering for asset selection, considering past wealth evolution.
result Strategy effectively learns from past performance and performs well in practice.
RCRC model extracts features quickly and efficiently for reinforcement learning tasks.
problem High computational costs in training reinforcement learning models.
method Convolutional Reservoir Computing (RCRC) model using random fixed-weight CNN and reservoir computing.
result RCRC model achieves state-of-the-art scores in reinforcement learning tasks.
This tutorial introduces the CMA Evolution Strategy (ES), where CMA stands for Covariance Matrix Adaptation. The CMA-ES is a stochastic, or randomized, method for real-parameter (continuous domain) optimization of non-linear, non-convex functions. We try to motivate and derive the algorithm from intuitive concepts and …
Evolution Strategies (ES) emerged as a scalable alternative to popular Reinforcement Learning (RL) techniques, providing an almost perfect speedup when distributed across hundreds of CPU cores thanks to a reduced communication overhead. Despite providing large improvements in wall-clock time, ES is data inefficient whe…
Analyzes how venture investment strategies have evolved over time in different sectors.
problem Understanding changes in venture investment strategies across sectors over time.
method Applied PCA and TCA to analyze a dataset of 52,000 startups and 110,000 funding rounds.
result There has been a shift in venture investment towards lower-tech sectors and a rise in accelerator investments.
CR-FM-NES improves NES for high-dimensional optimization.
problem High-dimensional black-box optimization problems.
method CR-FM-NES extends FM-NES with a restricted covariance matrix representation.
result CR-FM-NES achieves significant speedup in high-dimensional problems.
Algorithm improves vanilla option pricing accuracy during and before COVID-19.
problem Improving vanilla option pricing accuracy during and before the pandemic.
method Combinational Mutation Strategy of Differential Evolution (CmDE) algorithm for bi-objective optimization.
result Algorithm approximates real market vanilla option prices more accurately than Black-Scholes.
ES-MAML uses Evolution Strategies for MAML, avoiding second derivative estimation.
problem Solving the MAML problem with efficient second derivative estimation.
method Applies Evolution Strategies to MAML, avoiding second derivative estimation.
result ES-MAML performs competitively and often better with fewer queries.
ES optimization improved by structured control variates.
problem Improving accuracy of Evolution Strategies in RL.
method RL-specific variance reduction through structured control variates.
result Structured control variates outperform general variance reduction methods.
Investment strategies in financial markets can lead to instability due to market impacts.
problem Market impacts make it impossible for investors to accurately optimize their strategies.
method Built an agent-based model with technical analysis strategy agents to investigate optimization instability.
result Investment strategies' parameters never converged but continued to change, leading to unstable market price evolution.
New sampling method reduces variance in correlated high-dimensional distributions.
problem Reducing variance in Monte Carlo estimators for correlated high-dimensional distributions.
method DPPMC (Determinantal Point Processes Monte Carlo) method for structured sampling.
result DPPMCs improve state-of-the-art in various optimization and machine learning problems.
EvoNet predicts the evolution of dynamic graphs using a graph neural network and recurrent architecture.
problem Predicting the evolution of dynamic graphs is challenging and underexplored.
method EvoNet uses a graph neural network and recurrent architecture to predict the evolution of dynamic graphs.
result EvoNet effectively predicts the evolution of dynamic graphs on both artificial and real-world datasets.
Algorithm learns which weights to share in deep multi-task learning.
problem Difficulty in deciding which weights to share between tasks in deep learning models.
method Combines natural evolution strategy and stochastic gradient descent to learn optimal weight sharing.
result Task-specific networks achieve lower test errors than existing methods on multi-task learning datasets.
NES optimizes discrete structured VAEs effectively without gradient propagation.
problem Learning high-dimensional discrete latent spaces in generative models.
method Natural Evolution Strategies (NES) for gradient-free optimization of discrete structures.
result NES effectively optimizes discrete structured VAEs, comparable to gradient-based methods.
Graph neural network using Beltrami flow for feature and topology evolution.
problem Efficient feature learning and topology evolution on graphs.
method Discretized Beltrami flow applied to graph neural networks with positional encodings.
result Achieves state-of-the-art results on various benchmarks.
Investigates spectral properties of neural networks, showing invariance under certain conditions.
problem Understanding the spectral evolution and invariance in linear-width neural networks.
method Empirical and theoretical analysis of spectra of weight matrices in high-dimensional settings.
result Spectra of weight matrices are invariant under certain training conditions, with implications for feature learning.
We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients. Experiments on MuJoCo and Atari show that ES is a viable solution strategy that scales extremely well with the number of CPUs avail…
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.
Gradients help find global optima in complex functions.
problem Finding global optima in functions with many local minima.
method A principle for generating search directions from non-local quadratic approximants based on gradients.
result The proposed algorithm and CMA-ES perform better than random reinitialized BFGS.
DeepStreamCE detects new classes in streaming deep neural networks.
problem Detecting new classes in deep neural networks in a streaming environment.
method Uses autoencoder and MCOD stream-based clustering for real-time concept evolution detection.
result DeepStreamCE outperforms OpenMax in identifying concept evolution.
We propose a methodology for clustering financial time series of stocks' returns, and a graphical set-up to quantify and visualise the evolution of these clusters through time. The proposed graphical representation allows for the application of well known algorithms for solving classical combinatorial graph problems, w…
This paper explores the problem of unknotting closed braids and classical knots in mathematical knot theory. We apply evolutionary computation methods to learn sequences of moves that simplify knot diagrams, and show that this can be effective both when the evolution is carried out for individual knots and when a gener…
This version withdrawn by arXiv administrators because the submitter did not have the right to agree to our license at the time of submission.
Improves BED scalability for implicit models.
problem Designing experiments for implicit models with intractable data distributions.
method Hybrid gradient approach combining variational MI estimator, ES, and SGA.
result Significantly improves scalability of BED for implicit models.
We develop a more efficient NGD method for structured parameters.
problem Computational challenges in NGD for structured parameter spaces.
method Local-parameter coordinates to simplify Fisher-matrix computations.
result New structured second-order algorithms and learning methods.
Neural networks model COVID-19 spread with partial isolation data.
problem Modeling the spread of COVID-19 with limited data.
method Semi-supervised neural networks solving inverse problems.
result Estimates optimal conditions for virus spread and passive population.
Trading strategies evolve in a simulated market to outperform real data.
problem Creating profitable trading strategies in diverse market conditions.
method Agent-based model of heterogeneous agents evolving deep neural networks.
result Elite trading algorithms outperform in real high-frequency foreign exchange data.
Enhanced neural network framework improves constraint satisfaction with topological conditioning.
problem Maintaining semantic coherence while satisfying physical and logical constraints in neuro-symbolic reasoning.
method Integrates topological conditioning with gradient stabilization mechanisms using Forman-Ricci curvature, Deep Delta Learning, and Covariance Matrix Adaptation Evolution Strategy.
result Achieves mean energy reduction to 1.15 compared to baseline values of 11.68, with 95 percent success rate.
A new ES method improves reinforcement learning speed and accuracy.
problem Slow convergence and local maxima in reinforcement learning.
method Directional Gaussian Smoothing Evolution Strategy (DGS-ES)
result DGS-ES accelerates RL training with high accuracy and nonlocal search direction.
Latest algorithms for automatic neural architecture search perform remarkable but are basically directionless in search space and computational expensive in training of every intermediate architecture. In this paper, we propose a method for efficient architecture search called EENA (Efficient Evolution of Neural Archit…
Evolution and learning are two of the fundamental mechanisms by which life adapts in order to survive and to transcend limitations. These biological phenomena inspired successful computational methods such as evolutionary algorithms and deep learning. Evolution relies on random mutations and on random genetic recombina…
New paradigm for Neural ODEs stabilizes training and improves model performance.
problem Gradient vanishing-explosion problem in training deep neural networks.
method ODEtoODE: Nested system of flows with orthogonal group constraints.
result Strong convergence results and improved downstream models in reinforcement learning and supervised learning.
Parallel score matching accelerates DPM training and improves density estimation.
problem Extended training periods and limited modeling flexibility in DPMs.
method Partitioning the learning task into independent time sub-intervals and modeling the score at each time point separately.
result Significant acceleration of training process and improved density estimation performance.
This paper presents Natural Evolution Strategies (NES), a recent family of algorithms that constitute a more principled approach to black-box optimization than established evolutionary algorithms. NES maintains a parameterized distribution on the set of solution candidates, and the natural gradient is used to update th…
Reproductive success and survival are influenced by wealth in human populations. Wealth is transmitted to offsprings and strategies of transmission vary over time and among populations, the main variation being how equally wealth is transmitted to children. Here we propose a model where we simulate both the dynamics of…
We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines and with provable theoretical guarantees. We show that this algorithm can be successfully applied to learn better quality compact policies …
Differentiable NAS frameworks grow networks wider and deeper, revealing biases in wiring evolution.
problem Understanding the evolution of neural architecture wiring in differentiable NAS methods.
method Unified view on searching algorithms, local cost minimization, empirical and theoretical analyses.
result Implicit inductive biases cause observed searching patterns in differentiable NAS methods.