New approach to multi-armed bandit problem aims to maximize highest total reward.
problem Traditional multi-armed bandit problem objective of maximizing total reward is not suitable in certain applications.
method Adaptive explore-then-commit policy with confidence bounds and adaptive stopping criterion.
result Achieves asymptotic and worst-case regret bounds for the new objective.
This research reverses feature visualization in neural networks to optimize for specific feature objectives.
problem The invertibility of feature visualization in neural networks is not well understood.
method The approach involves optimizing for the feature objective that generates the input used in feature visualization, using the gradient of a specific objective function.
result A closed-form solution is found to minimize the gradient, providing an alternative view on network sensitivity.
This work improves GAN training by optimizing multiple discriminator losses.
problem Training GANs with multiple discriminators using single-objective methods.
method Formulates multi-objective optimization of multiple discriminator losses.
result Hypervolume maximization outperforms previous methods in sample quality and computational cost.
Proposes a framework to maximize mutual information in VAE models for better latent code representation.
problem Lack of explicit measurement of the quality of learned representations in VAE models.
method Variational Mutual Information Maximization Framework for VAE.
result Maximizes mutual information between latent codes and observations, improving latent code representation.
We classify the torsion pairs in a tube category and show that they are in bijection with maximal rigid objects in the extension of the tube category containing the Pruefer and adic modules. We show that the annulus geometric model for the tube category can be extended to the larger category and interpret torsion pairs…
A method for learning from unlabeled time-series data using temporal smoothing and entropy maximization.
problem Learning from unlabeled time-series data efficiently and accurately.
method Training a feedforward neural network with two objectives: temporal smoothing and entropy maximization.
result The method extracts slowly evolving information from time-series data, filtering out noise.
New method for fair influence maximization in social networks.
problem Maximizing influence while ensuring fairness across sensitive attributes.
method Co-training an auto-encoder and discriminator to create fair graph embeddings.
result Our method reduces disparity while maintaining competitive influence maximization performance.
New guarantees for adaptive combinatorial maximization with various objectives.
problem Maximizing under cardinality constraints and minimum cost coverage in adaptive settings.
method Bayesian approach with comprehensive approximation guarantees for various utility functions.
result Maximal gain ratio is a new parameter that provides stronger approximation guarantees than greedy policies.
Satisficing is a relaxation of maximizing and allows for less risky decision making in the face of uncertainty. We propose two sets of satisficing objectives for the multi-armed bandit problem, where the objective is to achieve reward-based decision-making performance above a given threshold. We show that these new pro…
VFunc models functions efficiently, maximizing objectives like data likelihood and entropy.
problem Efficiently modeling and optimizing functions for complex objectives.
method Deep generative model p(f, z) with variational lower bound on entropy.
result Maximizes objectives involving data likelihood and entropy.
A new method for multi-objective Bayesian optimization using entropy search and variational lower bound maximization.
problem Efficiently optimizing multiple objectives in continuous domains.
method Approximates the Pareto-frontier using a mixture distribution and optimizes the balance through variational lower bound maximization.
result Demonstrated effectiveness especially with many objective functions.
In this paper, we propose an active perception method for recognizing object categories based on the multimodal hierarchical Dirichlet process (MHDP). The MHDP enables a robot to form object categories using multimodal information, e.g., visual, auditory, and haptic information, which can be observed by performing acti…
Paper estimates optimal ROC curve arc length and AUC, improving classification performance.
problem Estimating optimal ROC curve arc length and AUC in imbalanced binary classification.
method Expresses arc length and AUC as variational objectives, estimating using positive and negative samples.
result Proposed classification procedure maximizes an approximate lower bound of maximal AUC.
Algorithm maximizes review quality of least advantaged paper and ensures accurate paper acceptance.
problem Fair and accurate assignment of papers to reviewers in peer review.
method Incremental max-flow procedure for fairness, minimax analysis for accuracy.
result Near-optimal fairness and accuracy of paper assignment.
Solves the VAE learning issue by optimizing a more informative generator.
problem Learning issue in VAE where only one model can be optimal at a time.
method Introduces Variational InfoMax (VIM) learning objective to optimize both inference and generative models.
result Derives a learning objective that optimizes both inference and generative models.
A new algorithm solves sparse reward tasks efficiently in robotics.
problem Sparse or misleading rewards in reinforcement learning.
method Multi-objective model-based policy optimization with three objectives.
result Multi-DEX solves sparse reward scenarios in fewer episodes than existing methods.
New training method improves model performance across various tasks.
problem Training deep neural networks using only the ground-truth class information.
method Maximizes likelihood of ground-truth classes while neutralizing complement classes.
result Training with both primary and complement objectives improves model performance across multiple tasks.
We consider learning of submodular functions from data. These functions are important in machine learning and have a wide range of applications, e.g. data summarization, feature selection and active learning. Despite their combinatorial nature, submodular functions can be maximized approximately with strong theoretical…
A new method balances accuracy and diversity in ensemble pruning.
problem Balancing accuracy and diversity in ensemble learning.
method Formalizing ensemble pruning as an objection maximization problem based on information entropy, proposing a distributed framework.
result Achieves less time-consuming execution with minimal accuracy degradation.
New approach categorizes objective functions for embodied agents.
problem Understanding how objectives relate to each other and discovering new objectives.
method Introducing Action Perception Divergence (APD) to categorize objective functions.
result Introduces a spectrum of objectives from narrow to general, explaining various unsupervised objectives.
Study private submodular maximization in streaming data.
problem Private maximization of submodular functions in streaming data.
method Established differentially private baselines and derived better trade-offs for decomposable submodular functions.
result Improved trade-offs between privacy and utility for decomposable submodular functions.
Bayesian quadrature optimization tackles uncertainty in distributional samples.
problem Maximizing an expensive black-box integrand under distributional uncertainty.
method Distributionally robust optimization perspective, posterior sampling.
result Empirical effectiveness and theoretical convergence demonstrated.
This paper improves monaural source enhancement using SDR as an objective function.
problem Maximizing signal-to-distortion ratio (SDR) for better monaural source enhancement.
method Uses signal-to-distortion ratio (SDR) as an objective function to improve monaural source enhancement.
result The proposed method achieved better performance than conventional methods.
We study the problem of maximizing a monotone set function subject to a cardinality constraint k in the setting where some number of elements τ is deleted from the returned set. The focus of this work is on the worst-case adversarial setting. While there exist constant-factor guarantees when the function is submodu…
Bayesian optimization tackles expensive discrete and mixed parameter spaces.
problem Optimizing expensive functions with discrete and mixed parameters.
method Probabilistic reparameterization to maximize expectation of AF over continuous parameters.
result Our approach provably converges to a maximizer of the AF and enjoys the same regret bounds as standard BO.
The study finds that maximizing median returns is the only viable strategy in portfolio selection.
problem Difficulties in studying optimal portfolio strategies due to discontinuity and time inconsistency in maximizing median and quantile returns.
method Used intra-personal equilibrium approach to analyze portfolio selection under median and quantile maximization.
result Median maximization is the only viable strategy, with no investment in risky assets for other quantiles.
A new method for diverse Pareto solutions in multi-objective learning.
problem Maximizing diversity while maximizing hypervolume in Pareto solutions.
method Annealed Stein Variational Gradient Descent (SVGD) with diverse gradient directions.
result SVH-MOL achieves superior performance in multi-objective and multi-task learning.
TES optimizes black-box functions efficiently with minimal approximations.
problem Efficient Bayesian optimization with minimal approximations and generalization to batch BO.
method TES acquisition function measures information gain on trusted maximizers.
result TES achieves state-of-the-art performance with minimal approximations.
New algorithm finds global maxima in multi-modal functions.
problem Finding global maxima in multi-modal functions with saddle points.
method G-PFSO algorithm using particle filter and averaging.
result G-PFSO efficiently finds global maximizer at optimal rate.
Proposes a framework to reconcile policy learning and profit maximization in CATE estimation.
problem Aligning CATE estimation with profit maximization for optimal customer treatment decisions.
method Optimizes a novel objective function that concentrates learning capacity near the decision boundary, ensuring consistency with the original profit function.
result Consistent CATE estimates can be recovered from existing profit-maximization pipelines, allowing firms to navigate the trade-off between accuracy and profit.
A new framework extracts informative features from multiple data types.
problem Finding maximally correlated feature representations from multimodal data.
method Soft-HGR framework, which relaxes whitening constraints while preserving feature geometry.
result Soft-HGR learns more informative feature mappings and is more efficient to optimize.
Proposes a framework to improve VAE latent codes using mutual information.
problem Lack of explicit measure for VAE latent variable quality.
method Variational Mutual Information Maximization Framework.
result Improves relationships between latent codes and observations.
Study maximal orders to find surfaces without genus 212.
problem Which genera can be obtained by closed congruence surfaces?
method Investigate maximal orders in quaternion algebras to construct surfaces.
result No surface of genus 212 can be constructed by maximal orders.
DIM learns deep representations by maximizing mutual information, outperforming unsupervised methods.
problem Learning useful representations from unlabeled data.
method Maximizing mutual information between input and output of a deep neural network encoder, incorporating prior knowledge.
result DIM outperforms other unsupervised learning methods and competes with fully-supervised learning on classification tasks.
InfoCatVAE learns disentangled representations for categorical data.
problem Learning disentangled representations for categorical data.
method InfoCatVAE uses multimodal distributions and maximizes the ELBO objective, connecting it to a soft clustering objective.
result Improved model with mutual information maximization.
We develop parallel predictive entropy search (PPES), a novel algorithm for Bayesian optimization of expensive black-box objective functions. At each iteration, PPES aims to select a batch of points which will maximize the information gain about the global maximizer of the objective. Well known strategies exist for sug…
New optimization method for portfolio management maximizing wealth and utility with risk control.
problem Maximizing terminal wealth and utility with mean-variance risk control.
method Transformed into a single-objective problem using overall happiness, solved in game theoretic framework.
result Closed-form solutions for specific utility functions reveal new optimal investment strategies.
Adaptive cascade submodular maximization tackles sequential selection under uncertainty.
problem Maximizing expected utility from a set of items with unknown states and continuation probabilities.
method Proposed adaptive cascade submodular functions and a 0.12 approximation algorithm.
result Identified a class of functions (adaptive cascade submodular) that many practical applications satisfy.
Many online companies sell advertisement space in second-price auctions with reserve. In this paper, we develop a probabilistic method to learn a profitable strategy to set the reserve price. We use historical auction data with features to fit a predictor of the best reserve price. This problem is delicate - the struct…
Maximizes Rényi entropy for efficient exploration in reward-free RL.
problem Challenges of exploration in reward-free reinforcement learning.
method Maximizes Rényi entropy over state-action space in exploration phase; uses batch RL for planning phase.
result Effective and sample-efficient exploration leading to superior policies.
MIRO learns robust latent spaces by maximizing mutual information with future information.
problem Robust perception in complex, unstructured environments with low sample complexity.
method MIRO maximizes mutual information in a latent space for model-based reinforcement learning.
result MIRO outperforms reconstruction objectives in cluttered scenes.
GoBOED optimizes experiments for specific decision-making objectives, improving downstream outcomes.
problem Reducing parameter uncertainty does not always improve decision-making in critical settings.
method Combines variational posterior surrogate and differentiable convex decision layer for gradient-based design optimization.
result GoBOED identifies designs that better align with specific decision objectives and reveals wider optimal design windows.
Optimal algorithm for submodular maximization in distributed networked scenarios.
problem Maximizing submodular functions under distributed matroid constraints.
method Constraint-Distributed Continuous Greedy (CDCG) algorithm.
result Achieves a (1−1/e) approximation factor, significantly outperforming sequential greedy methods. The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.
problem Learning structured representations from unlabeled data.
method Adversarial maximization of mutual information between a structured latent variable and a target variable.
result The proposed method outperforms current baselines in document hashing and yields highly compressed interpretable representations.
Paper tackles multi-block min-max optimization with applications in deep AUC maximization.
problem Multi-block min-max bilevel optimization with non-convex strongly-concave upper level and strongly convex lower level.
method Single-loop randomized stochastic algorithm for constant number of blocks per iteration.
result Sample complexity of O(1/ε^4) for finding ε-stationary point, matching optimal complexity.
We develop a model to study the role of rationality in economics and biology. The model's agents differ continuously in their ability to make rational choices. The agents' objective is to ensure their individual survival over time or, equivalently, to maximize profits. In equilibrium, however, rational agents who maxim…
The paper proposes a new approach to portfolio selection that maximizes diversification and return.
problem Maximizing diversification and return in portfolio selection.
method A bi-objective model that maximizes a diversification measure and portfolio expected return.
result The return-diversification approach outperforms strategies based on diversification or classical risk-return approaches.
We establish the existence and characterization of a primal and a dual facelift - discontinuity of the value function at the terminal time - for utility-maximization in incomplete semimartingale-driven financial markets. Unlike in the lower- and upper-hedging problems, and somewhat unexpectedly, a facelift turns out to…