Algorithm estimates bounds of updated classifier coefficients efficiently.
problem Determining sensitivity of updated classifiers without retraining.
method Proposes an algorithm to estimate upper and lower bounds of updated classifier coefficients.
result Estimates bounds with low computational complexity and tightness.
AMUSE uses reinforcement learning to predict optimal model updates.
problem Concept drift weakens model performance over time.
method Reinforcement learning in a simulated environment.
result AMUSE proactively recommends updates based on performance improvements.
DeepCCG adapts classifiers to representation shifts in one step.
problem Adapting classifiers to shifts in continuous representation.
method Empirical Bayesian approach using class conditional Gaussian classifier and KL divergence for selection.
result DeepCCG reduces performance change due to representation shifts.
Survey of methods for classifier comparison using precision.
problem Lack of methods for classifier comparison using precision.
method Statistical methods for precision comparison, accounting for inter-precision correlation.
result Methods to test global null hypothesis of model comparison using precision.
Improved classifiers by updating log-loss bounds during optimization.
problem Overemphasis on incorrectly classified examples far from decision boundary.
method Updating the log-loss upper bound during optimization.
result Improved classification rates and linking classifier performance to system constraints.
A new classifier updates sequentially using maximum margin principles.
problem Sequential data collection and partial labeling.
method Maximum margin classifier with Maximum Entropy Discrimination principle, kernel representation, and regularization.
result Improved performance compared to non-sequential classifiers.
Bayesian inference improved with classifier-based misspecification detection and tempering.
problem Model misspecification in Bayesian inference leads to overly concentrated posteriors.
method Probabilistic classifiers trained on simulated vs. observed data to estimate model misspecification and tempering level.
result Estimation of negative KL divergence provides useful diagnostic and update method.
Optimal adversarial noise algorithms for multiple classifiers using game theory.
problem Designing robust attacks against multiple classifiers.
method Formulating the problem as a two-player, zero-sum game and using Multiplicative Weights Update framework with best response oracles.
result Demonstrated the effectiveness of randomization in adversarial attacks and optimal mixed strategies.
We introduce a novel sensitivity analysis framework for large scale classification problems that can be used when a small number of instances are incrementally added or removed. For quickly updating the classifier in such a situation, incremental learning algorithms have been intensively studied in the literature. Alth…
A method for combining classifiers from multiple views using Bregman divergences.
problem Combining classifiers from multiple views with limited labeled data.
method Jointly learns view-specific and overall weighted majority vote classifiers using Bregman divergences.
result Empirical results show improved classifier performance with limited labeled data.
New framework reduces strategic manipulation cost for minority groups in fair classification.
problem Strategic manipulation disparities in fair classification.
method Constrained optimization framework that constructs classifiers to reduce strategic manipulation cost for minority groups.
result Empirically, the approach reduces strategic manipulation cost for minority groups over multiple real-world datasets.
A new algorithm finds a separating hyperplane with fewer updates.
problem Finding a separating hyperplane with minimal updates.
method Optimistic Perceptron algorithm.
result The Optimistic Perceptron finds a separating hyperplane with no more than $ rac{1}{γ}$ updates.
Efficiently updates classifiers after small dataset modifications.
problem Updating classifiers quickly after small dataset changes in large-scale problems.
method Proposes a method to bound optimal classifiers without re-training.
result Provides bounds on optimal classifiers with low computational cost.
Bayesian approach updates pretrained convnet for new image categories.
problem Learning new categories with limited data.
method Bayesian procedure using pretrained convnet weights as prior.
result Competitive performance with state-of-the-art methods.
Recently, prediction markets have shown considerable promise for developing flexible mechanisms for machine learning. In this paper, agents with isoelastic utilities are considered. It is shown that the costs associated with homogeneous markets of agents with isoelastic utilities produce equilibrium prices correspondin…
This work generates training-time adversarial data using auto-encoders to manipulate classifiers.
problem Manipulating the behavior of trained classifiers during test time with bounded perturbation.
method An auto-encoder-like network generates perturbations, learning to update weights to produce harmful noise.
result The method can manipulate classifiers effectively, showing good transferability.
New PAC-Bayes method updates priors without losing confidence information.
problem Lack of sequential prior updates in PAC-Bayes without losing confidence information.
method Recursive PAC-Bayes decomposition of expected loss.
result Sequential prior updates with no information loss.
MTL2L learns to adapt optimisation rules for unseen data.
problem Learners need to adapt to unseen data domains.
method Introduces MTL2L, a context-aware neural optimiser.
result MTL2L can adapt optimisation rules for unseen data.
Proposes a system to explain black box classifier outputs.
problem Providing understandable explanations for complex models.
method Extends Turner's (2015) MES to explain positive predictions in credit card fraud detection.
result Able to explain single predictions from black box classifiers.
A new method improves EEG classification across subjects efficiently.
problem Challenges in adapting and retaining knowledge for EEG classifiers across different subjects.
method Meta UPdate Strategy (MUPS-EEG) for continuous EEG classification.
result Outperforms current state-of-the-art methods in adapting to new subjects and retaining knowledge of learned subjects.
Paper introduces a new adversarial attack type that cheats classifiers with significant changes.
problem Cheating well-trained classifiers with small permutations.
method Supervised variation autoencoder and gradient-based updates to latent variables.
result The proposed attack significantly cheats classifiers with significant changes, reducing Type I error.
A new method for estimating sparse inverse covariance matrices.
problem Recovering the connectivity and non-connectivity graph of covariates.
method Adaptive thresholding in a transformed domain of the inverse covariance matrix.
result The proposed method outperforms state-of-the-art methods in accuracy.
We propose an active set selection framework for Gaussian process classification for cases when the dataset is large enough to render its inference prohibitive. Our scheme consists of a two step alternating procedure of active set update rules and hyperparameter optimization based upon marginal likelihood maximization.…
Local elasticity in neural networks makes predictions resilient to dissimilar updates.
problem Understanding resilience of neural network predictions to updates from dissimilar data.
method Simulation and geometric interpretation using neural tangent kernel.
result Local elasticity persists in neural networks with nonlinear activation functions, not in linear ones.
BOIL updates model body only, showing better few-shot learning performance.
problem Few-shot learning efficiency with model reuse vs. change.
method Proposes BOIL, updating only model body, freezing head.
result Significantly outperforms MAML on cross-domain tasks.
Fuzzy eIX method evolves classifiers for online data streams.
problem Handling time-varying classifiers in online data streams.
method Develops evolving Internal-eXternal Fuzzy granules for numerical data.
result Fuzzy eIX maintains high accuracy in dynamic scenarios.
End-to-end framework learns new classes dynamically.
problem Challenges in recognizing unseen classes in real-world settings.
method Dynamic cascade of classifiers that incrementally learn features.
result Outperforms existing methods on real-world datasets.
We present a new online boosting algorithm for adapting the weights of a boosted classifier, which yields a closer approximation to Freund and Schapire's AdaBoost algorithm than previous online boosting algorithms. We also contribute a new way of deriving the online algorithm that ties together previous online boosting…
Paper proposes a classifier to improve medical image classification with limited data.
problem Limited training data leads to overfitting in medical image classification.
method Uses reinforcement learning to update classifier parameters with generalization feedback from a subset of training data.
result Improves classification performance and demonstrates generalized learning.
Model forgets examples; this research predicts which ones to replay.
problem Language models forget examples during updates, leading to errors.
method Train forecasting models to predict which examples will be forgotten.
result Forecasting models can reduce forgetting of upstream pretraining examples.
Self-training improves generalization by fitting to reliable pseudo-labels or gradually improving the classification plane.
problem Understanding how self-training improves generalization in high-dimensional Gaussian mixtures.
method Analyzing iterative self-training on binary Gaussian mixtures in the asymptotic limit.
result ST improves generalization by fitting to reliable pseudo-labels or gradually improving the classification plane.
CILF learns adaptive embeddings for class-incremental learning with novel class detection and model update.
problem Handling unknown classes and model update in streaming data with new classes.
method CILF uses decoupled prototype based loss for intra-class and inter-class structure improvement, and a learnable curriculum clustering operator for adaptive embedding.
result CILF effectively detects multiple novel classes and mitigates embedding confusion, while updating the model without catastrophic forgetting.
A novel minimax classifier tackles imbalanced datasets with few minority samples.
problem Imbalanced datasets with limited minority samples.
method Proposes a novel minimax learning algorithm with two steps: minimization and maximization.
result The algorithm improves model performance compared to existing methods.
A method for consensus prediction from probabilistic classifier outputs.
problem Combining probabilistic classifier outputs without prior information.
method Iteratively updating predictions based on classifier diversity and convergence.
result Consensus predictions converge to a decision based on classifier outputs' correspondence.
Exact PA algorithms learn to rank with interval labels.
problem Learning to rank with interval labels.
method Exact passive-aggressive algorithms solving convex optimization problems.
result Maintains threshold ordering and achieves accurate classifiers.
Adaptive weighting improves Deep Forest classifier's performance.
problem Improving Deep Forest classifier's efficiency and accuracy.
method Adaptive weighing of training instances at each cascade level, inspired by AdaBoost.
result The modified Deep Forest classifier performs better than the original.
A framework for prototype-based classifiers in changing data environments.
problem Learning in non-stationary environments with concept drift.
method Analytical methods from statistical physics applied to LVQ systems.
result Basic LVQ algorithms are suitable for non-stationary environments, but weight decay does not improve performance.
Sketches linear classifiers using Weight-Median Sketch for efficient data stream analysis.
problem Efficiently learning and analyzing data streams with limited memory.
method Introduces Weight-Median Sketch for compressed linear classifier learning over data streams.
result Memory-limited execution of various analyses over streams, including feature selection and mutual information estimation.
Differentially private ensemble classifiers adapt to data streams while protecting privacy.
problem Adapting to evolving data characteristics while protecting private information.
method Unbounded ensemble updates, model agnostic approach.
result Outperforms competitors on various privacy, drift, and distribution settings.
Framework for efficient defect classification and inspection.
problem Adaptive defect classification and inspection from high volume data.
method Continual learning framework for dynamic classifier updates.
result Efficient storage and computational needs reduction.
Mobile agents classify images via reinforcement learning and consensus.
problem Image classification using multiple mobile agents.
method Proposed network architecture for local belief formation and feature extraction. Decentralized consensus protocol using reinforcement learning.
result Effectiveness of the proposed framework demonstrated on MNIST dataset.
Modified Perceptron handles strategic agents with limited position changes.
problem Learning linear classifiers in the presence of strategic agents that can manipulate their positions.
method Developed a modified Perceptron algorithm with bounded mistakes under various manipulation costs.
result The modified Perceptron achieves bounded mistakes even when manipulation costs are unknown.
Bayesian classifier predicts journey routes using Markov chains.
problem Predicting the route of ongoing journeys.
method Modeling journey patterns as stochastic processes and updating posterior probabilities with Markov chains.
result High accuracy in route predictions demonstrated on synthetic data.
Paper studies deep learning attacks on online APIs with limited data.
problem Adversarial machine learning threats on online APIs with strict rate limitations.
method Develops an active learning approach to build adversarial classifiers with limited training data.
result Active learning can build adversarial classifiers with small statistical difference from target classifiers using limited data.
Develops a novel GAN method for better image generation.
problem Training stability and generalization in GANs.
method LD-GAN trains discriminator to maximize separability and generator based on LDA.
result Improved training stability and generalization in class conditional generation.
The condensed nearest neighbor (CNN) algorithm is a heuristic for reducing the number of prototypical points stored by a nearest neighbor classifier, while keeping the classification rule given by the reduced prototypical set consistent with the full set. I present an upper bound on the number of prototypical points ac…
Paper defines a new distance metric for comparing learning tasks.
problem Comparing difficulty of learning tasks between source and target.
method Information geometry, optimal transport, coupled transfer distance.
result Coupled transfer distance correlates with fine-tuning difficulty.
In distributed learning, the goal is to perform a learning task over data distributed across multiple nodes with minimal (expensive) communication. Prior work (Daume III et al., 2012) proposes a general model that bounds the communication required for learning classifiers while allowing for $\eps$ training error on lin…