Develops auction theory for real-life applications with positive valuations.
problem Real-life auction settings with positive valuations and interdependent bidders.
method Approximations using log-normal distribution, positive symmetric discrete distribution, and interdependent valuations.
result New auction theory results applicable to finance and procurement.
GANs can learn hierarchical distributions in real-world images efficiently.
problem Understanding and efficiently learning complex, real-world distributions with GANs.
method Formally studying how GANs can learn hierarchically generated distributions close to real-life image distributions using SGDA.
result Training GANs via SGDA can efficiently learn distributions with a 'forward super-resolution' structure, both in sample and time complexities.
The study examines denoising and noisy-input regression under distribution shift, revealing double descent behavior and insights for data augmentation.
problem Understanding denoising in machine learning, especially under noisy inputs and distribution shift.
method Theoretical analysis of supervised denoising and noisy-input regression, considering low-rank data and proportional regime.
result The test error exhibits double descent under general distribution shift, indicating that overfitting the noise can be benign, tempered, or catastrophic.
New research shows encoder-decoder GANs can still fail even on real data.
problem Theoretical limitations of Encoder-Decoder GAN architectures.
method Rigorous analysis of Encoder-Decoder GAN training objectives.
result The training objectives cannot prevent mode collapse or learning meaningless codes.
End-to-end deep learning detects emotions in real-life emergency calls.
problem Recognizing emotions in real-life emergency call center recordings.
method Used an end-to-end deep learning architecture trained on IEMOCAP and CEMO datasets.
result Obtained 45.6% Unweighted Accuracy Recall on CEMO with 4 classes, 76.9% on 2 classes (Anger, Neutral).
K-nearest neighbors (KNN) method is used in many supervised learning classification problems. Potential Energy (PE) method is also developed for classification problems based on its physical metaphor. The energy potential used in the experiments are Yukawa potential and Gaussian Potential. In this paper, I use both app…
Paper presents a robust model to improve prediction accuracy for real-life mobile phone data.
problem Noisy instances in real-life mobile phone data affect model accuracy.
method Identify and eliminate noisy instances using naive Bayes and Laplace estimators, then build a decision tree model.
result The robust model improves prediction accuracy as shown by experimental results.
Study shows sample noise impacts active learning performance.
problem Impact of sample noise on active learning performance.
method Proposed Incremental Weighted K-Means for noisy samples.
result Robust sampler improves synthetic tasks but only marginally in real-life.
New bound for neural nets on non-iid data.
problem Generalization of deep nets for dependent data.
method Establishes a generalization bound for feed-forward neural networks on φ-mixing data. result Proves neural nets can generalize well on non-iid data.
Proposes a new method to model event sequences using normalizing flows.
problem Modeling asynchronous and probabilistic event sequences.
method Intensity-free framework using normalizing flows.
result Effective at capturing stochasticity of discrete event sequences.
Neural eliminators reduce unreliable classification by eliminating improbable classes.
problem Unreliable classification due to noise, insufficient data, overlapping distributions, and unclear class definitions.
method Construct eliminators using classifiers with modified error functions, assigning cases to multiple classes instead of one.
result Elimination of improbable classes improves classification accuracy in real-life medical applications.
Paper proposes a copula method to generate unfavorable VaR scenarios.
problem Creating unfavorable VaR scenarios for insurance models.
method Patchwork copulas to create unfavorable VaR scenarios with given marginal distributions.
result Demonstrated with a 19-dimensional real-life insurance losses data set.
Missing data is a significant problem impacting all domains. State-of-the-art framework for minimizing missing data bias is multiple imputation, for which the choice of an imputation model remains nontrivial. We propose a multiple imputation model based on overcomplete deep denoising autoencoders. Our proposed model is…
This paper studies how to capture dependency graph structures from real data which may not be Gaussian. Starting from marginal loss functions not necessarily derived from probability distributions, we utilize an additive over-parametrization with shrinkage to incorporate variable dependencies into the criterion. An ite…
RegFlow models future states with flexible probability distributions.
problem Predicting future states under complex, non-deterministic scenarios.
method Hypernetwork architecture and continuous normalizing flow model.
result RegFlow achieves state-of-the-art results on benchmark datasets.
New algorithms improve reinforcement learning for complex tasks.
problem Improving reinforcement learning for complex tasks.
method Developed new algorithms using distributional reinforcement learning and Cram{é}r distance.
result Proved asymptotic almost-sure convergence of new algorithms for neural networks.
New algorithm predicts spatio-temporal events with improved accuracy.
problem Non-stationary spatio-temporal prediction on dense and sparse sequences.
method Probabilistic approach using point processes and self-organizing decision trees.
result Significant performance improvements over baseline and state-of-the-art methods.
SHMM models human mobility from GPS and text data, overcoming text sparsity.
problem Modeling human mobility from semantic trace data, especially addressing text sparsity.
method SHMM is a multi-modal spherical hidden Markov model that jointly models location, time, and text embeddings on a unit sphere using vMF distribution.
result SHMM outperforms state-of-the-art models in next location prediction and has lower training cost.
A new method aligns source and target distributions by tuning their weights.
problem Domain adaptation on unlabeled target datasets using labeled source datasets.
method Weighted Joint Distribution Optimal Transport (WJDOT) method that finds alignment between source and target distributions and re-weighting of source distributions.
result Achieves state-of-the-art performance on simulated and real-life datasets.
Proposes a new method for feature selection in non-linear functions.
problem Feature selection for non-linear functions in high-dimensional data.
method Continuous relaxation of Bernoulli distributions to learn feature selection indicators via gradient descent.
result Demonstrates the effectiveness of the approach on synthetic and real-life applications.
Study compares resampling methods for rare event prediction in longitudinal studies.
problem Predicting rare events in longitudinal follow-up studies.
method Comparison of resampling methods to improve standard regression models.
result Effect of sampling rate on model predictive performance.
This paper presents a simple but effective density-based outlier detection approach with the local kernel density estimation (KDE). A Relative Density-based Outlier Score (RDOS) is introduced to measure the local outlierness of objects, in which the density distribution at the location of an object is estimated with a …
We extend probabilistic programming to handle conditioning on marginal distributions.
problem Conditioning probabilistic programs on marginal distributions of observable variables.
method We define and implement stochastic conditioning, allowing inference in probabilistic programs conditioned on marginal distributions.
result We demonstrate the effectiveness of stochastic conditioning in various real-life scenarios.
A new measure identifies clusters without assuming data distribution.
problem Identifying the correct number of clusters in data without distribution assumptions.
method Nonparametric interpoint distance-based approach.
result Superior to existing clustering measures, validated on synthetic and real data.
New algorithm clusters multiple samples from hidden distributions.
problem Traditional clustering algorithms cannot handle multiple samples from non-Gaussian distributions.
method Proposes a general framework for multiple sample clustering, generating various algorithms.
result Sufficient statistics improve clustering accuracy and stability.
This paper introduces a novel technique to track structures in time evolving graphs. The method is based on a parameter free approach for three-dimensional co-clustering of the source vertices, the target vertices and the time. All these features are simultaneously segmented in order to build time segments and clusters…
New method samples from piecewise smooth distributions using Hamiltonian Monte Carlo.
problem Sampling from distributions with discontinuous gradients.
method Generalized Randomized Hamiltonian Monte Carlo (GRHMC) for piecewise smooth targets.
result GRHMC processes sample from piecewise smooth target distributions with the desired distribution as the invariant distribution.
This paper compares communication efficiency of split learning and federated learning in various scenarios.
problem Comparing communication efficiency of split learning and federated learning in different settings.
method Examined various practical scenarios of distributed learning setups and compared the two methods.
result Communication efficiency of split learning and federated learning depends on the number of clients, model size, and data samples.
We analyze empirical data for 4,000 real-life trading portfolios (U.S. equities) with holding periods of about 0.7-19 trading days. We find a simple scaling C ~ 1/T, where C is cents-per-share, and T is the portfolio turnover. Thus, the portfolio return R has no statistically significant dependence on the turnover T. W…
An artificial stock market is established based on multi-agent . Each agent has a limit memory of the history of stock price, and will choose an action according to his memory and trading strategy. The trading strategy of each agent evolves ceaselessly as a result of self-teaching mechanism. Simulation results exhibit …
A new sampling method balances imbalanced data using gamma distribution.
problem Imbalanced class distribution in data causes bias in classification algorithms.
method Intelligent resampling of minority class instances via gamma distribution.
result The proposed method outperforms existing techniques on 12 out of 24 datasets.
We design, conduct and present the results of a highly personalized baseline emotion recognition experiment, which aims to set reliable ground-truth estimates for the subject's emotional state for real-life prediction under similar conditions using a small number of physiological sensors. We also propose an adaptive st…
Unsupervised neural network learns graph embeddings for various tasks.
problem Efficiently representing and comparing families of graphs for mining tasks.
method An unsupervised neural network approach to learn graph embeddings.
result Our method outperforms graph distances and kernels in clustering and classification tasks.
In this paper, we show an approach to build deep learning algorithms for recognizing signals in distributed fiber optic monitoring and security systems for long perimeters. Synthesizing such detection algorithms poses a non-trivial research and development challenge, because these systems face stringent error (type I a…
A new model predicts spatio-temporal data using adaptive decision trees and point processes.
problem Predicting spatio-temporal data with real-life applications.
method Hawkes process, adaptive decision tree, joint optimization algorithm.
result Significant improvement in predictions compared to standard methods.
RL agents learn to detect and mitigate adversarial attacks.
problem Adversarial attacks on Deep RL algorithms deployed in real-life applications.
method Meta-Learned Advantage Hierarchy (MLAH) agent using meta-learning for online robustness.
result The MLAH agent exhibits hierarchical coping behaviors and maintains higher reward distributions over time.
Paper proposes a method to detect out-of-distribution examples using variational inference.
problem Uncertainty in deep neural networks for unseen examples.
method Variational Dirichlet framework to approximate higher-order distribution and use entropy as uncertainty measure.
result Demonstrated to consistently outperform competing algorithms on various datasets.
Investor optimizes portfolio under VaR constraint with heavy-tailed stock returns.
problem Managing Value at Risk (VaR) for portfolios with heavy-tailed stock price returns.
method Formulated a dynamic optimisation problem using stochastic maximum principle, approximating the value function and optimal strategy without explicit solutions.
result Close concordance with financial intuition, providing insights for high-frequency traders.
This work proposes a two-level framework for anomaly detection in sequences using GANs.
problem Detecting anomalies in sequences of discrete elements, especially when they are unknown or rare.
method The approach involves assessing statistics from discriminator layers and building an unsupervised anomaly detection module. GANs are used to augment data and track known data classes.
result The method successfully detects anomalies in sequences of discrete elements, improving detection accuracy and timeliness.
This paper introduces a novel technique to track structures in time varying graphs. The method uses a maximum a posteriori approach for adjusting a three-dimensional co-clustering of the source vertices, the destination vertices and the time, to the data under study, in a way that does not require any hyper-parameter t…
This paper explores using KDE for balanced sampling in imbalanced datasets.
problem Imbalanced class distribution in data science.
method Kernel density estimation (KDE) for resampling the minority class.
result KDE-based resampling outperforms other techniques in F1-score and G-mean.
New approach to fairness in machine learning using contrastive questions.
problem Ensuring fairness in algorithmic decision-making.
method Causal inference to address contrastive fairness.
result Mathematical tools for contrastive fairness in machine learning.
IFGAN uses feature-specific GANs for missing value imputation.
problem Missing value imputation in data mining.
method Feature-specific Generative Adversarial Networks (GAN).
result IFGAN outperforms state-of-the-art algorithms in various missing conditions.
Superensemble classifier improves predictions in imbalanced datasets.
problem Imbalanced datasets lead to poor performance in minority class examples.
method Maps Hellinger distance decision trees into RBFN framework for universal consistency and parameter optimization.
result The proposed model outperforms state-of-the-art models in various real-life data sets.
Proposes a new approach to enforce uniform distribution on torus.
problem Enforcing uniform distribution on torus for generative models.
method Introduces circular spring loss to enforce equally spaced points on torus.
result Enables morphing between points on torus with different paths.
modAL simplifies active learning in Python.
problem Making active learning research and practice easier.
method Clear, modular design; compatibility with scikit-learn.
result Facilitates fast prototyping and algorithm development.
In the era of deep learning several unsupervised models have been developed to capture the key features in unlabeled handwritten data. Popular among them is the Restricted Boltzmann Machines RBM. However, due to the novelty in handwritten multidialect data, the RBM may fail to generate an efficient representation. In t…
Proposes a deep generative model for robust forecasting on sparse multivariate time series.
problem Forecasting on sparse multivariate time series with suboptimal results when sparsity is high.
method Dynamic Gaussian Mixture distribution for modeling latent clusters, using neural networks and gating mechanism.
result Demonstrates robust modeling of sparse multivariate time series with improved accuracy.