New framework improves adversarial robustness in one-stage L2D.
problem Adversarial robustness in one-stage Learning-to-Defer (L2D).
method Formalizes attacks, proposes cost-sensitive adversarial surrogate losses, establishes theoretical guarantees.
result Improves robustness against untargeted and targeted attacks while preserving clean performance.
Simpler algorithm learns shallow networks faster.
problem Learning a linear combination of ReLU activations.
method A simpler one-stage algorithm with improved runtime.
result Runs in (d/ε)O(k2) time. We propose a two-stage hybrid approach with neural networks as the new feature construction algorithms for bankcard response classifications. The hybrid model uses a very simple neural network structure as the new feature construction tool in the first stage, then the newly created features are used as the additional i…
Paper proposes ARB-Loss to improve classification precision in imbalanced datasets.
problem Improving classification precision on minor classes in imbalanced datasets.
method Introduces Attraction-Repulsion-Balanced Loss (ARB-Loss) to balance gradients across different classes.
result ARB-Loss achieves state-of-the-art performance with one-stage training.
Unified model for prediction and deferral selects top-k entities efficiently.
problem Efficiently selecting top-k entities for deferral in machine learning.
method One-stage Top-k Learning-to-Defer framework with a convex surrogate. result Unified model achieves superior accuracy-cost trade-offs.
Enhanced privacy, utility, and efficiency through MUST subsampling.
problem Balancing privacy, utility, and computational efficiency in data analysis.
method MUltistage Sampling Technique (MUST) for privacy amplification in differential privacy.
result MUST offers stronger privacy guarantees (ϵ) than one-stage subsampling methods while maintaining similar utility and computational efficiency. We present the Integrated Size and Price Optimization Problem (ISPO) for a fashion discounter with many branches. Based on a two-stage stochastic programming model with recourse, we develop an exact algorithm and a production-compliant heuristic that produces small optimality gaps. In a field study we show that a distr…
Generative adversarial networks (GAN) have recently been shown to be efficient for speech enhancement. However, most, if not all, existing speech enhancement GANs (SEGAN) make use of a single generator to perform one-stage enhancement mapping. In this work, we propose to use multiple generators that are chained to perf…
Principal component regression (PCR) is a two-stage procedure that selects some principal components and then constructs a regression model regarding them as new explanatory variables. Note that the principal components are obtained from only explanatory variables and not considered with the response variable. To addre…
This paper proposes a Residual Convolutional Neural Network (ResNet) based on speech features and trained under Focal Loss to recognize emotion in speech. Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCCs) have shown the ability to characterize emotion better than just plain text. Furth…
Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.
problem Limitation of existing L2D frameworks to single-expert deferral.
method Top-k Learning-to-Defer framework, including adaptive Top-k(x) variant. result Superior accuracy-cost trade-offs with multi-expert deferral.
End-to-end kernel learning using generative RFFs for improved performance.
problem Improving kernel learning performance and generalization.
method Develops a generative network via RFFs to implicitly learn the kernel, followed by a linear classifier, jointly trained by ERM.
result Shows superior generalization performance over classical methods in real-world tasks.
Paper develops a new method for distribution regression with indefinite kernels.
problem Distribution regression with indefinite kernels.
method Coefficient-based regularized distribution regression with two-stage sampling.
result Optimal learning rates derived for the algorithm under mild conditions.
A new PCR method using SVD with sparse regularization.
problem Lack of response variable information in traditional PCR.
method One-stage SVD approach with two loss functions and sparse regularization.
result Obtains principal component loadings with response variable information.
New RL algorithm reduces policy switching cost to loglog(T) with similar regret.
problem Low policy switching cost in real-life RL applications.
method Stage-wise exploration and adaptive policy elimination.
result Regret of O(HSAloglogT) with O(HSAloglogT) switching cost. Recently, researchers utilize Knowledge Graph (KG) as side information in recommendation system to address cold start and sparsity issue and improve the recommendation performance. Existing KG-aware recommendation model use the feature of neighboring entities and structural information to update the embedding of curren…
Currently, there starts a research trend to leverage neural architecture for recommendation systems. Though several deep recommender models are proposed, most methods are too simple to characterize users' complex preference. In this paper, for a fine-grain analysis, users' ratings are explained from multiple perspectiv…
New model uses pretrained biochemical language models to generate drug compounds.
problem Developing novel compounds targeting specific proteins.
method Exploits pretrained language models to initialize and fine-tune targeted molecule generation models.
result Warm-started models outperform baseline models, with one-stage strategy showing better generalization.
Let R be an o-minimal expansion of the real field, and let L(R) be the language consisting of all nested Rolle leaves over R. We call a set nested subpfaffian over R if it is the projection of a boolean combination of definable sets and nested Rolle leaves over R. Assuming that R admits analytic cell decomposition, we …
Object detection in point cloud data is one of the key components in computer vision systems, especially for autonomous driving applications. In this work, we present Voxel-FPN, a novel one-stage 3D object detector that utilizes raw data from LIDAR sensors only. The core framework consists of an encoder network and a c…
Principal component regression (PCR) is a widely used two-stage procedure: principal component analysis (PCA), followed by regression in which the selected principal components are regarded as new explanatory variables in the model. Note that PCA is based only on the explanatory variables, so the principal components a…
New algorithm achieves strong consistency in binary non-uniform hypergraph classification.
problem Node classification on binary non-uniform hypergraphs with varying edge probabilities.
method Proposes a refinement algorithm using power iteration on weighted adjacency matrices.
result Proves optimality of the refinement algorithm, achieving strong consistency and IT lower bound.
The recent application of deep learning in various areas of medical image analysis has brought excellent performance gains. In particular, technologies based on deep learning in medical image registration can outperform traditional optimisation-based registration algorithms both in registration time and accuracy. Howev…
The paper introduces new Bayesian network classifiers for better classification accuracy.
problem Improving supervised classification accuracy using Bayesian network classifiers.
method Developed novel classes of generative classifiers based on staged tree models, extending Bayesian networks.
result Data-driven learning routines enhance the accuracy of the new classifiers.
RLHF uses human feedback to train AI models, posing statistical challenges.
problem Aligning AI models with human preferences using noisy, subjective feedback.
method Supervised fine-tuning, reward modeling, policy optimization, statistical ideas.
result Statistical methods for reward function learning and policy optimization.
Object detection models shipped with camera-equipped edge devices cannot cover the objects of interest for every user. Therefore, the incremental learning capability is a critical feature for a robust and personalized object detection system that many applications would rely on. In this paper, we present an efficient y…
A new multi-view clustering method that is fast, scalable, and easy to use.
problem High computational complexity, one-stage fusion, and dataset-specific hyperparameter tuning in multi-view clustering.
method Random view groups, hybrid early-late fusion, diversified base clusterings, and unified bipartite graph.
result Almost linear time and space complexity, no dataset-specific tuning required.
A new framework integrates credit scoring into profit scoring for better P2P lending investments.
problem Maximizing profit while minimizing risk in P2P lending investments.
method Two-stage framework using Light Gradient Boosting Machine (lightGBM) to integrate credit scoring into profit scoring.
result The proposed framework identifies more profitable loans and provides better investment guidance.
Empirical risk minimization is the main tool for prediction problems, but its extension to relational data remains unsolved. We solve this problem using recent ideas from graph sampling theory to (i) define an empirical risk for relational data and (ii) obtain stochastic gradients for this empirical risk that are autom…
This work extends reduction processes for nonholonomic discrete mechanical systems.
problem Nonholonomic discrete mechanical systems and their reductions.
method Introduces a category LDPd of discrete-time dynamical systems and a two-stage reduction process. result Two-stage reduction process produces systems isomorphic to one-stage reduction.
Supervised learning frequently boils down to determining hidden and bright parameters in a parameterized hypothesis space based on finite input-output samples. The hidden parameters determine the attributions of hidden predictors or the nonlinear mechanism of an estimator, while the bright parameters characterize how h…
A machine learning method for short-maturity options with jumps and stochastic volatility.
problem Short-maturity options with jumps and stochastic volatility.
method Differential machine learning method combining supervision and PIDE-residual penalty.
result Improves jump-term approximation and reduces Greeks errors compared to baselines.
Paper proposes online optimization for uncertain systems using machine learning and DRO.
problem Optimization of uncertain dynamical systems with distributional uncertainty.
method Combines machine learning with Distributional Robust Optimization (DRO) to handle uncertainty.
result Online solutions with probabilistic regret bounds for uncertain systems.
New classifiers account for context-specific independences.
problem Restrictions in generative models for classification.
method Staged tree classifiers that account for context-specific independences.
result Staged tree classifiers achieve competitive classification accuracy.
Proposes Contrastive Clustering for improved clustering performance.
problem Improving clustering performance on various datasets.
method Instance- and cluster-level contrastive learning through data augmentations and feature space projections.
result Contrastive Clustering achieves significant improvements over 17 competitive methods.
Bayesian optimization tackles expensive cascade processes.
problem Optimizing multistage decision-making processes with expensive costs.
method Formulated as Bayesian optimization framework with two types of acquisition functions.
result Demonstrated effectiveness through numerical experiments and a solar cell simulator application.
Study optimizes product assortment for retailers with repeated exposures and patience costs.
problem Optimizing product assortment for online retailers with repeated exposures and varying consumer patience.
method Developed a cascade multinomial logit model to capture repeated exposures and patience costs.
result Proposed an approximation solution to the assortment optimization problem.
The paper considers a class of multi-agent Markov decision processes (MDPs), in which the network agents respond differently (as manifested by the instantaneous one-stage random costs) to a global controlled state and the control actions of a remote controller. The paper investigates a distributed reinforcement learnin…
Improves classifier performance in multi-stage processes with adversarial autoencoders and multi-task learning.
problem Challenges in training classifiers due to varying sample sizes and information content across stages.
method Combines adversarial autoencoders, multi-task learning, and semi-supervised learning to address underfitting and overfitting.
result Our approach outperforms state-of-the-art methods across different domains.
FROST speeds up and stabilizes one-shot semi-supervised learning.
problem Slow training and sensitivity to labeled data choices in semi-supervised learning.
method Combines semi-supervised learning with a one-stage, single network self-training approach.
result FROST trains up to 10x faster and is more robust to labeled data choices.
A framework tackles model uncertainty in ALM, providing robust investment strategies.
problem Model uncertainty in asset liability management (ALM).
method Wasserstein barycenter approach to handle various information sources and uncertainties.
result The proposed framework selects robust investment portfolios that remain optimal under various uncertainties.
Proposes ML methods for robust price-sensitivity estimation in dynamic pricing.
problem Estimating price elasticities robustly in the presence of feature-dependent sensitivity.
method Poisson semi-parametric model with two-stage estimation: first-stage ML for observed purchases, second-stage Bayesian GLM for price-sensitivity.
result Reduces estimation error in price-sensitivity parameters from 25% to 4%.
End-to-end model for time series classification with missing data.
problem Time series classification with missing data.
method End-to-end neural network that unifies imputation and representation learning.
result Proposed model outperforms state-of-the-art approaches for incomplete time series classification.
Language models fail to execute simple steps, showing gating and binding errors.
problem Procedural hallucinations in language models, failing to execute simple steps.
method Analyzed long-context binding tasks, identifying gating and binding errors.
result Procedural errors are due to gating and binding failures, with recency bias contributing to the latter.
Improves classifier performance in multi-stage selection processes.
problem Difficulty in training classifiers in multi-stage selection processes due to varying sample sizes and information.
method Multi-Stage Transfer Learning (MSGTL) approach that uses knowledge from simpler classifiers trained in early stages to improve later stages.
result MSGTL outperforms other transfer learning methods in real-world selection process data.
We focus on the distribution regression problem: regressing to vector-valued outputs from probability measures. Many important machine learning and statistical tasks fit into this framework, including multi-instance learning and point estimation problems without analytical solution (such as hyperparameter or entropy es…
Examines algorithmic modeling across three cultures.
problem Tackles algorithmic modeling in different cultural contexts.
method Uses parametric regressions, interpretable algorithms, and complex algorithms.
result Extension of Leo Breiman's thesis to include cultural differences.
Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that UCB, M3, S or Exp3 algorithms have good behaviours on average in RMG. Besides, hedging algorithms have been shown to be effective on predi…