Ensemble validation shows selectivity penalties but variety benefits.
problem Selecting classifiers for ensemble models and their error bounds.
method Forming an ensemble from a set of hypothesis classifiers, selecting randomly, with an error bound formula.
result No penalty for using a richer hypothesis set if same fraction selected.
Pruning neural networks can improve test accuracy even with significant parameter reduction.
problem The tradeoff between generalization and stability in neural network pruning.
method Analysis of pruning behavior over training, focusing on instability and its relation to generalization.
result Pruning's benefit to generalization increases with its instability.
Empirical study shows overparameterization benefits unsupervised learning of latent variable models.
problem Improving optimization landscape in unsupervised learning with overparameterization.
method Synthetic and semi-synthetic experiments with various models and training algorithms.
result Overparameterization significantly increases the number of ground truth latent variables recovered.
A wide variety of machine learning algorithms such as support vector machine (SVM), minimax probability machine (MPM), and Fisher discriminant analysis (FDA), exist for binary classification. The purpose of this paper is to provide a unified classification model that includes the above models through a robust optimizat…
Isobenefit Lines can offer a certain range of applicability in Location Theory and Gravitational Models for Urban and Geography Economics, in positional decision processes made by citizens, and, last but not least, in land value and property market theories and analysis. The value of a land, or a property, in a generic…
Study explores D-Wave QA for RBM training, finds modest benefits but no significant improvements.
problem Improving RBM training using D-Wave quantum annealing.
method Hybrid sampling approach combining classical and D-Wave QA methods.
result No significant improvements in RBM training using D-Wave QA, but potential for CF mitigation.
Paper develops a new similarity metric for predicting stock market returns.
problem Predicting stock returns is challenging due to market stochasticity and various influencing factors.
method Case-based reasoning approach using historical pricing data and a novel similarity metric.
result Demonstrates the benefits of the novel similarity metric in predicting stock market returns.
Self-supervised learning enhances model robustness and uncertainty.
problem Improving model robustness and uncertainty estimation.
method Self-supervised learning without requiring labels.
result Self-supervised learning improves robustness to adversarial examples, label corruption, and input corruptions.
Review of neural network expressivity and architectures.
problem Understanding neural network expressivity across different architectures.
method Comprehensive overview of approximation results for various neural network types.
result Deep neural networks offer advantages over shallow ones for specific function classes.
Solves GAN mode collapse by assigning minibatches to multiple discriminators.
problem Mode collapse in GANs where models generate similar samples.
method Multiple discriminators, microbatching, and changing tasks.
result Promotes sample diversity in generated sets.
This work analyzes benefits and limitations of data augmentation and feature averaging in deep learning models.
problem Theoretical understanding of incorporating invariance into deep learning models is lacking.
method Data augmentation and feature averaging are analyzed in the context of invariance in deep learning.
result Training with data augmentation leads to better estimates of risk and gradients, and feature averaging reduces generalization error with convex losses.
Semi-supervised learning benefits the rich more than the poor, affecting fairness.
problem Disparate impact of semi-supervised learning on different sub-populations.
method Theoretical and empirical analysis of a broad family of SSL algorithms using pseudo-labels.
result Semi-supervised learning benefits the rich more than the poor, potentially violating fairness.
Improved pseudo-label accuracy in semi-supervised learning with Hermite polynomials.
problem Improving pseudo-label accuracy in semi-supervised learning.
method Substituting ReLU activations with Hermite polynomial activations in deep networks.
result Hermite polynomial activations yield significant improvements in pseudo-label accuracy and financial savings.
Hybrid quantum neural networks predict continuous variables.
problem Predicting continuous variables using quantum computing.
method Quantum classical hybrid neural networks for continuous variable prediction.
result Quantum neural networks outperform classical methods in continuous variable prediction.
New insights into experience replay in RL algorithms.
problem Understanding the impact of replay capacity and replay ratio in Q-learning.
method Systematic and extensive analysis of experience replay in Q-learning methods, focusing on replay capacity and replay ratio.
result Greater replay capacity significantly improves performance for certain algorithms, while other techniques offer limited benefit.
Functional tensors unify probabilistic programming with automatic differentiation.
problem Designing probabilistic programming systems that can handle diverse inference strategies.
method Introducing functional tensors that capture benefits of tensors and continuous probability distributions.
result Functional tensors enable parallel exact inference for various modeling motifs.
Improved speech enhancement with larger neural networks using novel embeddings and biases.
problem Decreased robustness of speech enhancement models to real-world use cases.
method Frequency-positional embeddings, semi-supervised training, biased loss function.
result Better performance on real recordings with improved large neural network architecture.
Active learning method reduces label queries for positive examples.
problem Minimizing label queries for identifying all positive examples.
method Repurposed support estimator as offline algorithm, and a simple active learning method.
result Improved excess query cost of O ~ ( n ( D − 1 ) / D ) \widetilde{O}(n^{(D-1)/D}) O ( n ( D − 1 ) / D ) compared to offline methods. Optimal resource allocation improves feature classification accuracy in noisy conditions.
problem Improving feature classification accuracy when features are noisy and resource allocation affects noise magnitude.
method Developed a method for computing optimal resource allocation in various scenarios.
result Non-uniform resource allocation can significantly enhance classification performance.
This workshop about triangulations of manifolds in computational geometry and topology was held at the 2014 CG-Week in Kyoto, Japan. It focussed on computational and combinatorial questions regarding triangulations, with the goal of bringing together researchers working on various aspects of triangulations and of foste…
We introduce supervised latent Dirichlet allocation (sLDA), a statistical model of labelled documents. The model accommodates a variety of response types. We derive an approximate maximum-likelihood procedure for parameter estimation, which relies on variational methods to handle intractable posterior expectations. Pre…
Improved accuracy in machine learning with Cross-Cluster Weighted Forests.
problem Improving accuracy in machine learning algorithms for datasets with clusters.
method Ensembling Random Forest learners trained on clusters determined by k-means.
result Significant improvements in accuracy and generalizability over traditional Random Forest.
Enhances portfolio optimization by considering competitor benchmarks and regret.
problem Optimizing portfolios relative to specified competitors and measuring performance accurately.
method Extends Relative Robust Portfolio Optimisation to include competitor benchmarks and introduces a new way to measure regret.
result Improved portfolio optimization with competitor benchmarks and a new method for measuring regret.
CHAMELEON uses RNNs to recommend news sequences better than other methods.
problem Improving news recommendation accuracy and catalog coverage.
method Hybrid meta-architecture CHAMELEON with RNNs for sequence modeling and side information.
result Significantly higher recommendation accuracy and catalog coverage.
Automatic differentiation---the mechanical transformation of numeric computer programs to calculate derivatives efficiently and accurately---dates to the origin of the computer age. Reverse mode automatic differentiation both antedates and generalizes the method of backwards propagation of errors used in machine learni…
Optimal transport distances, otherwise known as Wasserstein distances, have recently drawn ample attention in computer vision and machine learning as a powerful discrepancy measure for probability distributions. The recent developments on alternative formulations of the optimal transport have allowed for faster solutio…
GC-Flow uses graph flows for better clustering than traditional GCNs.
problem Traditional GCNs miss useful clustering information.
method Designing normalizing flows to replace GCN layers, creating a generative model.
result GC-Flow produces well-separated clusters while maintaining predictive power.
Monotonicity helps in safely optimizing unknown functions.
problem Sequentially maximizing an unknown function with safety constraints.
method Gaussian process with monotonicity assumption, inspired by GP-UCB and SafeOpt.
result The proposed M-SafeUCB algorithm achieves theoretical guarantees and safety.
HyperImpute improves iterative imputation by automatically selecting models and hyperparameters.
problem Imputing missing values in datasets with variable model specifications.
method Generalized iterative imputation framework that adapts and configures models and hyperparameters automatically.
result Demonstrates superior imputation accuracy compared to benchmarks.
TMLE improves unbiased estimation in public health studies.
problem Improving unbiased estimation in observational studies.
method Targeted Maximum Likelihood Estimation (TMLE) integrates machine learning and statistical theory.
result TMLE has been adopted by researchers worldwide, especially outside the US.
Improved visual representation learning with conditional negative sampling.
problem Learning strong unsupervised visual representations using contrastive learning.
method Introduce a family of mutual information estimators that sample negatives conditionally.
result Improves accuracy by 2-5% points on four standard image datasets.
The paper studies adversarial training for linear regression models.
problem Understanding the tradeoffs between robust and standard accuracy in adversarial training.
method Characterizes the fundamental tradeoff and specific adversarial training approach for linear regression with Gaussian features.
result Precise characterization of the standard and robust accuracy tradeoff in high-dimensional settings.
A model for choosing crypto assets based on security and stability.
problem Optimal selection of crypto assets considering security and stability.
method A recommender app-like system that presents pairs of crypto assets and collects investor preferences.
result A variety of possible outcomes for crypto asset investments and adoption.
The paper tackles dynamic matrix recovery from incomplete data, improving accuracy and sample complexity.
problem Improving matrix recovery from incomplete data using dynamic constraints.
method Proposes LOWEMS framework for dynamic matrix recovery and establishes error bounds.
result Establishes error bounds for LOWEMS in matrix sensing and completion models, quantifying benefits of dynamic constraints.
Differentiable NAS method optimizes network architecture and parameters efficiently.
problem Challenging to simultaneously guarantee effectiveness and efficiency in network architecture search.
method Differentiable architecture search with ensemble Gumbel-Softmax estimator.
result End-to-end mechanism for searching network architectures, discovering high-performance architectures efficiently.
This paper formalizes representation learning and shows its benefits.
problem Understanding and formalizing the benefits of representation learning techniques.
method Introducing a formal framework to study representation learning and its utility.
result Representation learning can be performed provably and efficiently under plausible assumptions.
Extracts high-quality monolingual datasets from web crawl data.
problem Improving text representation quality through larger corpora.
method Automated pipeline using deduplication and language identification, augmented with filtering for high-quality documents.
result Extracted massive high-quality monolingual datasets from Common Crawl.
High-capacity neural network ensembles often benefit more from high-capacity models than from increased diversity.
problem The performance of high-capacity neural network ensembles is often harmed by interventions that promote predictive diversity.
method A large-scale study of nearly 600 neural network classification ensembles, examining various interventions and architectures.
result Discouraging predictive diversity can be benign in large-network ensembles, and higher-capacity models often yield better performance than diverse architectures.
Muon optimizer improves federated learning performance.
problem Improving federated learning performance with Muon optimizer.
method Proposed FedMuon algorithm with orthonormalized update direction.
result FedMuon's learning rate is independent of problem-specific parameters.
The goal of temporal alignment is to establish time correspondence between two sequences, which has many applications in a variety of areas such as speech processing, bioinformatics, computer vision, and computer graphics. In this paper, we propose a novel temporal alignment method called least-squares dynamic time war…
Recurrent Ladder Networks improve iterative inference and temporal modeling.
problem Complex learning tasks requiring iterative inference and temporal modeling.
method Proposes a recurrent extension of Ladder networks.
result Shows close-to-optimal results on temporal modeling of video data and competitive results on music modeling.
Gradient-based algorithm improves model performance with triage.
problem Improving model accuracy with human expert involvement.
method Formal characterization of triage, optimal triage policy as deterministic threshold rule, gradient-based algorithm.
result Gradient-based algorithm finds triage policies and models with increasing performance.
New study finds targeting based on treatment effects outperforms risk-based targeting in social interventions.
problem Lack of accurate treatment effect estimates for machine learning-based targeting in social domains.
method Empirical assessment of targeting strategies using data from 5 real-world RCTs in various domains.
result Treatment effect-based targeting outperforms risk-based targeting, even with biased estimates.
Improved cooperation between levels boosts reinforcement learning performance.
problem Training multi-level policies in hierarchical reinforcement learning.
method Modeling policy optimization as a multi-agent process and inducing cooperation between sub-policies.
result Inducing cooperation between sub-policies leads to stronger and more sample-efficient policies.
New algorithm improves treatment effect estimation from observational data.
problem Estimating the benefits and harms of interventions from observational data.
method Develops a deep kernel regression algorithm and posterior regularization framework.
result Substantially outperforms state-of-the-art on various benchmarks datasets.
Hrrformer uses HRR to speed up self-attention for long sequences.
problem Infeasibility of using transformers with very long sequence lengths.
method Re-cast self-attention using Holographic Reduced Representations (HRR).
result Achieves near state-of-the-art accuracy with O ( T H log H ) \mathcal{O}(T H \log H) O ( T H log H ) time complexity and O ( T H ) \mathcal{O}(T H) O ( T H ) space complexity. Igeood detects out-of-distribution samples using information geometry.
problem Out-of-distribution (OOD) detection in machine learning systems.
method Igeood uses the Fisher-Rao geodesic distance to detect OOD samples from any pre-trained neural network.
result Igeood outperforms state-of-the-art methods on various network architectures and datasets.
New random forest algorithm improves regression with missing data.
problem Regression with missing data values.
method New random forest algorithm compared to existing techniques.
result Improved performance in quadratic errors and bias compared to existing methods.