Activates speech DNNs to generate understandable examples.
problem Difficulty in understanding DNN classifications for speech.
method Activation maximization to generate speech samples.
result Activation maximization can generate understandable speech samples.
New active learning strategy improves decision-making accuracy.
problem Maximizing decision-making accuracy in sequential data acquisition.
method Introduces a novel active learning criterion that maximizes expected information gain on the posterior decision distribution.
result Improved performance in decision-making accuracy compared to existing alternatives.
Novel active learning detects network nodes for community detection.
problem Detecting community structure in networks.
method Maximal Expected Model Change (MEMC) criterion for querying network nodes.
result MEMC detects nodes that maximize community assignment likelihood changes.
We optimize discounts to maximize influence spread in social networks.
problem Maximizing influence spread in social networks with fractional discounts.
method Developed an efficient (1-1/e)-approximation algorithm for NP-hard problem.
result Achieved an approximation of 1-1/e for influence maximization.
New method for online influence maximization in social networks.
problem Identifying influential nodes in social networks.
method Factorization of activation probabilities into latent factors on nodes, using upper confidence bound online learning.
result Significant reduction in regret with proposed algorithm.
Active inference minimizes expected free energy for optimal behavior.
problem Understanding and optimizing behavior in complex systems.
method Combines Bayesian decision theory, optimal Bayesian design, and the free energy principle.
result Active inference emerges as a unified framework for information-seeking, utility maximization, and goal-directed behavior.
Paper uses HodgeRank and information maximization for efficient crowdsourced ranking.
problem Crowdsourced ranking quality improvement with limited budget.
method Information maximization applied to HodgeRank for active sampling.
result Boosts sampling efficiency compared to traditional methods.
DAL uses disentanglement for automatic labeling in GAN-based active learning.
problem Reducing human labeling in GAN-based active learning.
method DAL leverages disentanglement in InfoGAN to automatically label datapoints, deciding human labeling based on disagreement with InfoGAN labels and label correction.
result DAL achieves better performance than existing GAN-based active learning approaches on image classification tasks.
Proposes a new active learning criterion to maximize classifier instability.
problem Efficiently train classifiers with minimal labeled data.
method Maximizes variance of output changes for unlabeled data.
result Achieves state-of-the-art performance in experiments.
Polynomial neural networks explore thresholds for maximum expressiveness.
problem Understanding the limits of polynomial neural networks' expressiveness.
method Introducing activation degree threshold to measure network expressiveness and proving its existence and upper bounds.
result Polynomial neural networks with equi-width architectures achieve the maximum expressiveness.
Active inference enhances RL by balancing exploration and exploitation.
problem Traditional RL's balance between exploration and exploitation is often suboptimal.
method Developed a new decision-making objective based on active inference.
result The new algorithm successfully balances exploration and exploitation on various RL benchmarks.
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.
New method for optimizing neural networks with quantized weights and activations.
problem Improving resource efficiency of deep neural networks.
method Mean-field theory applied to quantized activation networks.
result Closed-form equation for maximal trainable depth, showing Lmax∝N1.82. New method corrects active learning for distribution shifts and outliers.
problem Conventional active learning methods fail to account for test-time distribution.
method JEPIG, a hybrid of BALD and EPIG, maximizes expected predictive information gain.
result JEPIG outperforms conventional methods in active learning with distribution shifts.
Active learning improves medical image segmentation by selecting optimal samples.
problem Limited manual annotations in medical datasets.
method Maximizing information at network abstraction layer and using Borda-count for sample selection.
result Improved segmentation performance with active learning.
GOIMDA selects inputs to maximize expected influence on a goal functional, reducing data acquisition needs.
problem Challenges in active data acquisition for learning and optimization tasks in deep neural networks.
method GOIMDA uses inverse curvature and goal gradient to select inputs maximizing expected influence on a specified goal functional.
result GOIMDA achieves target performance with fewer labeled samples or function evaluations compared to baselines.
Cheshire optimizes social network activity by incentivizing users to post.
problem Maximize overall activity in social networks through user incentives.
method Modelled user actions with Hawkes processes and SDEs with jumps; used stochastic optimal control.
result Optimal incentivized actions are linearly related to current activity levels.
Survey of methods to visualize neural network features.
problem Understanding neural network activation patterns.
method Activation Maximization and Feature Visualization via Optimization.
result Probabilistic interpretation of AM techniques.
This paper explores portfolio management strategies to maximize alpha and minimize beta.
problem Maximizing returns while minimizing risk in investment portfolios.
method Examines asset allocation, diversification, active management, and risk management strategies.
result Combining these strategies optimizes portfolio performance.
The problem of active diagnosis arises in several applications such as disease diagnosis, and fault diagnosis in computer networks, where the goal is to rapidly identify the binary states of a set of objects (e.g., faulty or working) by sequentially selecting, and observing, (noisy) responses to binary valued queries. …
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.
iRDM selects unlabeled samples for regression without labels, improving model accuracy.
problem Selecting unlabeled samples for regression without label information.
method Iterative representativeness-diversity maximization (iRDM).
result iRDM significantly outperforms supervised ALR, especially with limited labeled samples.
Differentiable submodular maximization combines learning and optimization.
problem Learning and optimizing submodular functions separately.
method Interpreting greedy maximization as distributions, smoothing, and differentiating.
result The approach optimizes submodular functions with theoretical guarantees.
New framework improves fairness in small data settings.
problem Ensuring fairness in low-data environments.
method Combines posterior sampling exploration with fair classification.
result Framework maximizes accuracy while meeting fairness constraints.
PDBAL targets experiments for probabilistic models to maximize insights.
problem Designing experiments to yield valuable insights efficiently.
method Combines user-specified risk function with probabilistic model to adaptively choose designs.
result PDBAL consistently outperforms standard approaches in simulations and real-world drug screen data.
Active Federated Learning selects clients to maximize efficiency.
problem Minimizing bandwidth usage and maximizing model accuracy in federated learning.
method Clients are selected with a probability conditioned on the current model and client data to maximize efficiency.
result Reduces the number of required training iterations by 20-70% while maintaining the same model accuracy.
Bayesian adaptive designs can be biased by active learning, especially with misspecified models.
problem Active learning bias in Bayesian adaptive experimental designs.
method Analysis of linear and preference learning models, empirical testing.
result Model misspecification and noise influence active learning bias in Bayesian designs.
This study examines fees in AMMs to reduce losses from informed orderflow.
problem Minimizing losses from informed orderflow in AMMs.
method Modeling arbitrage dynamics and sensitivity to fee choices.
result Identified fees that mimic price directionality to reduce losses.
A faster method for optimizing DNA and protein sequences using machine learning.
problem Designing DNA and protein sequences with improved function.
method Activation maximization with a straight-through approximation and adaptive entropy variable.
result Fast SeqProp achieves up to 100-fold faster convergence and improved fitness optima.
The problem of human activity recognition is central for understanding and predicting the human behavior, in particular in a prospective of assistive services to humans, such as health monitoring, well being, security, etc. There is therefore a growing need to build accurate models which can take into account the varia…
Bal-PM reduces preference labeling costs for LLMs.
problem Efficiently acquiring human feedback for preference modeling in large language models.
method Bayesian Active Learning with entropy maximization in feature space.
result Bal-PM reduces the number of required preference labels by 33% to 68%.
Efficient deep learning for hyperspectral image classification using active learning.
problem Lack of good-quality labeled samples for deep learning in hyperspectral images.
method Weighted incremental dictionary learning for active selection of training samples.
result The proposed algorithm improves deep learning efficiency and effectiveness in hyperspectral image classification.
This paper studies how AMMs can minimize losses from arbitrage while retaining uninformed trading activity.
problem Minimizing losses from arbitrage in AMMs while retaining uninformed trading activity.
method Modeling arbitrage dynamics and sensitivity to fee choices, mapping to a random walk with a reward scheme.
result AMMs can maximize value retention by optimizing fee structures.
A model learns from valid examples while avoiding invalid ones to generate better data.
problem Generative models produce nonsense when fitting to observed data.
method Active distribution learning using an invalidity oracle.
result Improper distribution learning can be done with polynomial queries, unlike proper learning which requires exponentially many.
Estimates user preferences from noisy paired comparisons.
problem Estimating user preferences from noisy paired comparisons.
method Greedy information maximization strategies.
result Superior preference estimation over state-of-the-art methods.
O-MedAL optimizes medical image analysis with online active deep learning.
problem Improving accuracy in medical image analysis with limited labeled data.
method Online Active Deep Learning method that queries examples maximizing average distance to training set.
result Significant performance improvements, including 6.30% accuracy boost with 25% labeled data.
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.
Unified regularization framework for visualizing CNNs.
problem Visualizing concepts learned by convolutional neural networks.
method Mathematical framework unifying regularization methods, Sobolev gradients.
result Sobolev filters provide sharper reconstructions and better control over scales.
New insights into Gamma-Poisson model for count data.
problem Estimating topic/dictionary matrix robustness to rank over-specification.
method Rewriting GaP model free of score/activation matrix, leading to new MME algorithm.
result Automatic pruning of irrelevant dictionary columns observed empirically.
Improved bounds on neural network regions using activation histograms.
problem Bounding the number of affine regions in ReLU networks.
method Analysis of algebraic topology problem, extension of framework to subnetwork composition.
result Slightly tighter bounds and insights into parameter initialization.
Active sampling algorithm improves accuracy of inferred scores from pairwise comparisons.
problem Inference of accurate scores from time-consuming pairwise comparisons.
method Approximate message passing and expected information gain maximization.
result ASAP offers the highest accuracy of inferred scores compared to existing methods.
This paper improves SNN training by using multiple sample compartments.
problem Training SNNs with single-sample estimators leads to inaccurate log-likelihood estimates.
method Proposes a GEM-based online learning algorithm that uses multiple independent spiking signals.
result Significant improvements in log-likelihood, accuracy, and calibration with multiple compartments.
RUCA maximizes data utility while minimizing privacy risk.
problem Privacy breaches in big data applications.
method RUCA (Ratio Utility and Cost Analysis) for privacy-preserving data projection.
result RUCA significantly outperforms existing methods in minimizing privacy risk.
Adaptive quadrature improves Bayesian inference through active learning.
problem Efficiently estimating posterior densities in Bayesian inference.
method Sequential node selection using acquisition functions, combining interpolative surrogate models and quadrature rules.
result Positive estimation of marginal likelihood with improved accuracy.
Deep neural networks maximize variation when few nodes change activation.
problem Maximizing variation in deep neural networks.
method Theoretical analysis of ReLU activation function and layer node numbers.
result Maximal variation occurs when few nodes change activation.
Bayesian optimization selects experiments for causal structure learning in Gaussian process networks.
problem Discover causal relationships in non-linear systems with continuous variables.
method Bayesian active learning and Gaussian process priors combined with Bayesian optimization for experiment selection.
result Efficiently maximizes expected information gain in learning causal structure.
New active learning methods for Gaussian process improve predictive modeling of composite fuselage.
problem Improving predictive modeling of composite fuselage with limited training samples and uncertainties.
method Proposed two new active learning algorithms for Gaussian process considering uncertainties.
result The proposed approach realizes better prediction performance for automatic shape control of composite fuselage.
Active inference implemented for high-dimensional tasks shows efficient exploration and improved sample efficiency.
problem Achieving efficient exploration and learning in complex, uncertain environments.
method Active inference framework applied to high-dimensional tasks, with Bayesian evidence maximization.
result Order of magnitude increase in sample efficiency over model-free baselines.