This paper compares different activation functions in GLVQ models.
problem Improving performance of GLVQ models using different activation functions.
method Investigates and compares ReLU, sigmoid, and swish activation functions in GLVQ models.
result Different activation functions have varying impacts on GLVQ model performance.
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.
Paper introduces a new curriculum generation method for reinforcement learning.
problem Improving reinforcement learning performance and speed through curriculum learning.
method The paper proposes a novel curriculum generation paradigm based on progression and mapping functions.
result Empirical results show the new approach outperforms state-of-the-art algorithms.
Introduces new performance measures using scaled utility functions.
problem Performance measurement in financial contexts.
method Certainty equivalents defined via scaled utility functions, well-posed portfolio optimization problem under generic conditions.
result Link between portfolio dynamics, benchmark process, and utility function choice in the long-run setting.
Develops robust MDPs for unknown disturbances with performance guarantees.
problem Unknown disturbance distribution in MDPs.
method Empirical distribution, sublevel set of distance function, weak convergence, concentration inequality.
result Robust optimal value function converges to true optimal value function with increasing sample sizes.
The paper explores conditions for predicting optimization performance.
problem Lack of formal theoretical guarantees linking prediction and optimization performance.
method Exploring conditions for asymptotic convergence and exact quantification of optimization performance.
result Explicit theoretical relationship between prediction and optimization performance.
Deep neural networks perform poorly on smooth functions despite strong approximation theory.
problem The gap between deep learning theory and practical performance on smooth functions.
method Computational framework to study DNN performance, comparing against best-in-class methods.
result There is a crucial gap between DNN approximation theory and practical performance, but it can be closed.
Boosts Q-learning by using value function bounds.
problem Efficiently solving new tasks using past experience.
method Derives double-sided bounds on optimal value function and uses them to update Q-function.
result Boosted training performance through alternative Q-function update method.
Study finds simple model-agreement scores perform well in various error estimation scenarios.
problem Evaluating model performance on unseen distributions using disparate scoring functions.
method Rigorously studied popular scoring functions (confidence, local manifold smoothness, model agreement) independently of mechanism choice.
result Simple model-agreement scores outperform confidence- and smoothness-based scores in realistic settings with compromised training data.
Optimizes resource allocation for virtualized network functions based on performance profiles.
problem Mapping SLA performance requirements to dynamic virtualized infrastructure resources.
method Profile-based resource allocation using VNF performance datasets and machine learning models.
result A method to predict and recommend optimal resource allocation for network services.
New approach to handle ranking function variation in zero-shot NAS.
problem Variation in ranking function outputs due to randomness.
method Viewing ranking function output as a random variable and constructing a stochastic ordering.
result Stochastic ordering boosts performance in neural architecture search.
New forward performance processes for predictable market updates.
problem Creating predictable forward performance processes for market information.
method Developed a binomial model with dynamic parameters and solved an inverse investment problem.
result Established conditions for the existence and uniqueness of solutions to the inverse problem.
Paper optimizes DC pension fund management with VaR and relative performance constraints.
problem Optimizing DC pension fund performance under VaR and relative performance constraints.
method Introduced an auxiliary process to transform the problem into a self-financing problem, combined linearization, Lagrange dual, martingale, and concavification methods.
result Explicit investment strategies obtained for certain penalty and reward functions.
Automatically discovers effective activation functions for deep learning.
problem Inconsistent performance of novel activation functions in deep learning networks.
method Evolutionary search for general form, gradient descent for parameters.
result Significant performance improvements over ReLU and other functions.
Optimized nonlinearities enhance generalization in random feature models.
problem Improving generalization performance in random feature models.
method Analyzed and defined optimal nonlinearities from Gaussian model parameters.
result Optimized nonlinearities achieve better generalization performance than ReLU.
Survey of trainable activation functions in neural networks.
problem Improving neural network performance through trainable activation functions.
method Taxonomy and comparison of recent and past models of trainable activation functions.
result Many trainable activation functions are equivalent to adding neuron layers with fixed activation functions and simple constraints.
This paper evaluates different non-linear activation functions for deep neural networks on MNIST.
problem Improving performance of deep neural networks on MNIST classification task.
method Introduction and evaluation of various non-linear activation functions, analysis of deeper networks, and investigation of weight initialisation methods.
result Different activation functions have distinct characteristics and can improve performance on MNIST.
Study proposes a differentiable surrogate loss function for optimizing Fβ score in binary classification with imbalanced data.
problem Non-differentiability of Fβ score makes it unsuitable for optimization by gradient-based learning. method Investigated relationship between Fβ score and loss functions, proposed a differentiable surrogate loss function. result Gradient paths of the proposed surrogate Fβ loss function approximate the gradient paths of the Fβ score. No-PASt-BO improves GP-Hedge by reducing past influence and normalizing acquisition functions.
problem GP-Hedge's reliance on past performance can lead to poor acquisition function dominance.
method No-PASt-BO reduces past influence and normalizes acquisition functions.
result No-PASt-BO outperforms GP-Hedge on both synthetic and real-world tasks.
Label embedding (LE) is an important family of multi-label classification algorithms that digest the label information jointly for better performance. Different real-world applications evaluate performance by different cost functions of interest. Current LE algorithms often aim to optimize one specific cost function, b…
A new Universal Activation Function improves performance across various machine learning tasks.
problem Achieving near optimal performance in different machine learning tasks.
method Optimization algorithms evolve the UAF's parameters to match the optimal activation function for each task.
result The UAF converges to near optimal performance in classification, quantification, and reinforcement learning tasks.
New activation functions improve neural network performance for exoplanet classification.
problem Optimizing neural network performance for exoplanet classification with hard attribute removal.
method Investigation of novel activation functions using ODE and fixed point theory, followed by empirical validation.
result Optimal neural network performance achieved without tuning, comparable to traditional functions.
Goldilocks activation functions improve neural network performance.
problem Improving neural network performance and understanding signal transformation.
method Introducing Goldilocks activation functions that locally deform input signals.
result Goldilocks networks outperform or match SELU and RELU on CIFAR-10 and CIFAR-100 datasets.
Bayesian optimization is a sample-efficient method for black-box global optimization. How- ever, the performance of a Bayesian optimization method very much depends on its exploration strategy, i.e. the choice of acquisition function, and it is not clear a priori which choice will result in superior performance. While …
This paper explores optimising acquisition functions in Bayesian optimisation.
problem Optimising acquisition functions in Bayesian optimisation is challenging due to their non-convex nature.
method The authors derive compositional forms for acquisition functions and use them to recast maximisation as a compositional optimisation problem.
result The compositional approach to maximising acquisition functions shows empirical advantages across various tasks.
Develops a new method to learn kernels directly over function space.
problem Learning kernels for flexible function approximators.
method Functional Kernel Learning (FKL) using transformed Gaussian processes over spectral densities.
result Direct inference of functional posteriors over kernels enables rich representations.
Deep learning enhances options hedging performance.
problem Improving delta hedging for options using neural networks.
method Learning residuals between hedging function and implied Black-Scholes delta using neural networks.
result Deep learning significantly improves hedging performance, often by more than 100%.
LSH methods extend to function spaces for efficient similarity search.
problem Efficient similarity search in function spaces.
method Locality-sensitive hashing (LSH) extended to Lp spaces using function approximation or Monte Carlo techniques. result An LSH family for Wasserstein distance over continuous probability distributions.
Stochastic models analyze traffic network performance.
problem Evaluate traffic system performance.
method Stochastic cell transmission models, preference functionals, Gaussian process regression.
result Illustrated in two case studies.
FunBO uses LLMs to discover effective acquisition functions for Bayesian optimization.
problem Designing optimal acquisition functions for Bayesian optimization across diverse problems.
method FunBO leverages FunSearch, an LLM, to learn and evaluate new acquisition functions.
result FunBO discovers acquisition functions that generalize well and outperform existing methods.
New q-neurons improve neural network performance.
problem Improving neural network activation functions.
method Introducing q-neurons based on Jackson's q-derivatives with stochastic parameters. result Consistently improved performance over state-of-the-art activation functions.
The scalability of submodular optimization methods is critical for their usability in practice. In this paper, we study the reducibility of submodular functions, a property that enables us to reduce the solution space of submodular optimization problems without performance loss. We introduce the concept of reducibility…
We describe dynamics of financial market observables and apply to portfolio performance.
problem Lack of mathematical description of financial market observables.
method Rank-based models and functionally generated portfolios.
result Performance of functionally generated portfolios studied over short and medium-term horizons.
A new activation function FTS improves deep learning performance.
problem Hindered propagation of negative values in ReLU.
method Proposed Flatten-T Swish (FTS) activation function, evaluated on MNIST dataset.
result FTS with T=-0.20 improves MNIST classification accuracy by 1.15% on 8-layer DFNN.
New ODE-Block handles stateful layers with continuous-in-depth functions using basis functions.
problem Handling stateful layers in ODE-Nets.
method Formulate ODE-Block using continuous-in-depth functions with basis function expansions.
result Enables state-of-the-art performance and reduces memory footprint.
Paper evaluates squared-exponential covariance function for Gaussian processes with integral observations.
problem Evaluating double line integrals of the squared exponential covariance function in Gaussian processes.
method Proposes a new approach to reduce double integrals to a single integral using the error function and efficiently computed with numerical techniques.
result Shows superior numerical robustness and accuracy compared to existing methods.
New method for regularizing deep networks using function norms.
problem Difficulty in measuring function complexity in deep networks.
method Sampling-based approximations to weighted function norms.
result Improved performance on classification and image segmentation tasks.
Sharp bounds on binary model inference performance.
problem High-dimensional inference in binary models.
method Convex empirical risk minimization, sharp asymptotics, optimal performance bounds.
result Sharp predictions and optimal performance bounds for binary models.
Improves deep neural network training by optimizing activation function and initialization.
problem Inappropriate activation function selection can lead to poor training performance.
method Comprehensive theoretical analysis of the Edge of Chaos and tuning of initialization parameters and activation functions.
result Training acceleration and improved performance achieved by optimizing activation function and initialization.
New method improves auto-labeling accuracy by optimizing confidence functions.
problem Overconfident model scores lead to poor TBAL performance.
method Developed a new post-hoc method, Colander, to optimize TBAL confidence functions.
result Achieves up to 60% improvement in coverage over baseline methods.
MUMBO optimizes multiple tasks efficiently, even with low-cost related functions.
problem Efficiently optimizing multiple related functions with low-cost evaluations.
method Derives a novel multi-task version of entropy search.
result Robust performance with low computational overhead across various optimization challenges.
This work explores Target Networks and Functional Regularization in deep Reinforcement Learning.
problem Stability and performance issues in deep Reinforcement Learning due to target value instability.
method Proposes and studies an explicit Functional Regularization approach as a replacement for Target Networks.
result Functional Regularization improves performance and stability compared to Target Networks.
This work examines aggregation functions in Deep Set learning.
problem The sensitivity of Deep Set networks to aggregation function choices.
method Investigation of alternative aggregation functions, including learnable recurrent ones.
result Learnable aggregations improve performance, reduce hyper-parameter sensitivity, and generalize better.
New neural network uses differential equations for adaptable activation functions.
problem Fixed activation functions limit neural network performance and size.
method Introduces differential equation units (DEUs) that learn nonlinear activation functions.
result DEUs enable more compact networks with comparable performance.
Simpler GNNs perform well on graph classification tasks.
problem Understanding what Graph Neural Networks (GNNs) learn and their complexity.
method Dissected GNNs into graph filtering and set function, linearizing them separately.
result Linear graph filtering with non-linear set function is efficient and powerful.
Enhances functional classifier performance with new tree-based methods and unbiased feature importance assessment.
problem Challenges of high-dimensional functional data and biased feature importance assessment.
method Augmented functional classification trees and random forests with ad-hoc conditional permutations for unbiased feature importance.
result Significant enhancement in predictive power of functional classifiers through new feature importance assessment.
Adma proposes a flexible loss function for neural networks.
problem Static loss functions limit neural network performance.
method Introduces a flexible loss function that adapts to ANN complexity and data distribution.
result Flexible loss function achieves state-of-the-art performance.
Enhances classifier performance through feature space transformations and model selection.
problem Improving the accuracy of classifiers by reducing complexity.
method Combining feature mapping, prototype selection, and kernel function transformations to transform data into a more convenient distribution.
result Our methods produce competitive classifiers and are statistically different among them.