Study investigates one-shot semi-supervised learning for image classification.
problem Training deep networks requires many labeled samples, limiting adoption.
method Empirical investigation of FixMatch method for one-shot semi-supervised learning.
result Uneven class accuracy is a barrier to high performance in one-shot semi-supervised learning.
We present surrogate regret bounds for arbitrary surrogate losses in the context of binary classification with label-dependent costs. Such bounds relate a classifier's risk, assessed with respect to a surrogate loss, to its cost-sensitive classification risk. Two approaches to surrogate regret bounds are developed. The…
New algorithm for robust circular coordinates in recurrent time series data.
problem Inefficient and sensitive methods for finding circular coordinates on recurrent data.
method Subsampling, aligning, and averaging to correct uneven sampling density.
result More robust and efficient circular coordinates for neuronal recordings.
Distillation affects some classes more than others, impacting fairness and bias.
problem Distillation affects some classes more than others, impacting fairness and bias.
method Examined class-wise accuracy and fairness metrics (DPD, EOD) on models trained with different datasets.
result Increasing the distillation temperature improves the distilled student model's fairness and individual fairness.
Regularizes decision trees to reduce inference time by up to 4x with minimal accuracy loss.
problem Optimizing decision tree execution time on resource-constrained devices.
method Regularizes impurity computation during CART algorithm training to favor highly asymmetric distributions.
result Reduces inference time by up to 4x with minimal accuracy loss.
Using results by Donaldson and Auroux on pseudo-holomorphic curves as well as Duval's rational convexity construction, the paper investigates the existence of smooth Lagrangian surfaces representing 2-dimensional homology classes in complex projective surfaces. We prove that if the projective surface X is minimal, of g…
CNNs can develop blind spots due to uneven padding in feature maps.
problem Spatial bias in convolutional networks leads to blind spots in certain tasks.
method Identified and analyzed the role of padding in convolutional networks, proposing solutions to mitigate bias.
result Mitigating spatial bias improves model accuracy, especially in tasks like small object detection.
Bubbles are essential in certain economic models with high growth and low interest rates.
problem Asset price bubbles exceeding fundamental values.
method Developed the Bubble Necessity Theorem in economic models with specific growth and interest rate conditions.
result Bubbles are inevitable in certain economic scenarios with high growth and low interest rates.
A new clustering algorithm GDT improves on HDBSCAN for uneven data.
problem Data clustering with uneven distribution and high noise.
method GDT combines local and global structures, forming local clusters and estimating a global topological graph based on connectivity between clusters.
result GDT achieves SOTA performance on various datasets with low time complexity.
In binary classification framework, we are interested in making cost sensitive label predictions in the presence of uniform/symmetric label noise. We first observe that 0-1 Bayes classifiers are not (uniform) noise robust in cost sensitive setting. To circumvent this impossibility result, we present two schemes; un…
Deep learning predicts AMD progression from longitudinal fundus images.
problem Predicting future stages of age-related macular degeneration (AMD).
method InceptionV3 feature vectors, interval scaling, Recurrent Neural Network.
result 0.878 sensitivity, 0.887 specificity, 0.950 AUC.
To train good supervised and semi-supervised object classifiers, it is critical that we not waste the time of the human experts who are providing the training labels. Existing active learning strategies can have uneven performance, being efficient on some datasets but wasteful on others, or inconsistent just between ru…
Communication through e-mails remains to be highly formalized, conventional and indispensable method for the exchange of information over the Internet. An ever-increasing ratio and adversary nature of spam e-mails have posed a great many challenges such as uneven class distribution, unequal error cost, frequent change …
New spectral clustering method for graphs with uneven node degrees.
problem Challenges in community detection for graphs with heterogeneous degree distributions.
method Spectral clustering on spherical coordinates with degree correction.
result Improved performance in representing computer networks.
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifi…
This research debiases machine unlearning by using counterfactual examples.
problem Machine unlearning processes can be biased, leading to inaccurate results.
method Intervention-based approach using counterfactual examples to mitigate biases.
result The method outperforms existing baselines on evaluation metrics.
Fake engagement is one of the significant problems in Online Social Networks (OSNs) which is used to increase the popularity of an account in an inorganic manner. The detection of fake engagement is crucial because it leads to loss of money for businesses, wrong audience targeting in advertising, wrong product predicti…
Background elimination for noisy character images or character images from real scene is still a challenging problem, due to the bewildering backgrounds, uneven illumination, low resolution and different distortions. We propose a stroke-based character reconstruction(SCR) method that use a weighted quadratic Bezier cur…
New findings reveal discount regularization can be seen as a strong prior, leading to poor performance in unevenly sampled data.
problem Discount regularization leads to poor performance in unevenly sampled data.
method Equivalence theorem showing discount regularization as a strong prior, setting regularization parameters locally for individual state-action pairs.
result Discount regularization can be seen as a strong prior, leading to poor performance in unevenly sampled data.
Suppose you look at today's stock prices and bet on the value of the first digit. One could guess that a fair bet should correspond to the frequency of 1/9=11.11 for each digit from 1 to 9. This is by no means the case, and one can easily observe a strong prevalence of the small values over the large ones. The fir…
New method generates geolocated synthetic populations from real data.
problem Generating synthetic populations with explicit geographic coordinates.
method Mapping coordinates into a latent space using Normalizing Flows (NF), then combining with other features in a Variational Autoencoder (VAE).
result NF+VAE architecture outperforms existing methods in generating geolocated synthetic populations.
Study on droplet flow on uneven surfaces, proving existence and properties.
problem Understanding droplet movement on irregular surfaces.
method Existence of smooth flow and 1/2-Hölder continuous minimizing movement solutions.
result Properties of minimizing movements including comparison principles and uniform boundedness.
We study historical calibration of one- and two-factor models that are known to describe relatively well the dynamics of energy underlyings such as spot and index natural gas or oil prices at different physical locations or regional power prices. We take into account uneven frequency of data due to weekends, holidays, …
Traditionally, practitioners initialize the {\tt k-means} algorithm with centers chosen uniformly at random. Randomized initialization with uneven weights ({\tt k-means++}) has recently been used to improve the performance over this strategy in cost and run-time. We consider the k-means problem with semi-supervised inf…
GrateTile optimizes CNN feature map storage for efficient data access.
problem Efficient storage and access of sparse CNN feature maps.
method Divides feature maps into uneven-sized subtensors, compresses and stores them in a compressed yet accessible format.
result Average 55% DRAM bandwidth reduction with minimal indexing overhead.
We develop an approach to learn an interpretable semi-parametric model of a latent continuous-time stochastic dynamical system, assuming noisy high-dimensional outputs sampled at uneven times. The dynamics are described by a nonlinear stochastic differential equation (SDE) driven by a Wiener process, with a drift evolu…
Predicts accuracy of classifiers on unseen classes.
problem Unknown accuracy of classifiers on unseen classes.
method Defined rROC to estimate classifier accuracy on unseen classes.
result Robust algorithm CleaneX achieves better predictions.
Sparse random projection (RP) is a popular tool for dimensionality reduction that shows promising performance with low computational complexity. However, in the existing sparse RP matrices, the positions of non-zero entries are usually randomly selected. Although they adopt uniform sampling with replacement, due to lar…
New neural network improves MRI reconstruction for non-Cartesian data.
problem Improving MRI reconstruction for non-Cartesian data acquisitions.
method Density-compensated unrolled neural networks.
result Density-compensated unrolled neural networks outperform baselines.
Joint diffusion models improve data representation for both generation and prediction.
problem Inconsistent performance between generation and classification tasks in joint models.
method Extended vanilla diffusion model with a classifier for joint end-to-end training.
result Joint diffusion model outperforms state-of-the-art hybrid methods in classification and generation.
The paper examines how adversarial robustness affects accuracy disparity across different classes.
problem Understanding the impact of adversarial robustness on accuracy disparity across different classes.
method Linear classifiers under a Gaussian mixture model, decomposing the impact into inherent and imbalance effects.
result Adversarial robustness consistently degrades standard accuracy in balanced classes, but the class imbalance ratio plays a different role in accuracy disparity.
Regularizing for or against class selectivity in DNNs improves test accuracy.
problem The necessity and sufficiency of class selectivity in DNNs.
method Direct regularization of class selectivity in convolutional neural networks.
result Reducing class selectivity improves test accuracy, while increasing it decreases it.
The paper develops a method to learn robust decision policies from observational data, reducing high-cost outcomes.
problem Learning safe decision policies from observational data with high-risk outcomes.
method Develops a method to learn policies that reduce high-cost outcomes, valid under finite samples and uneven feature overlap.
result Validates the method with real and synthetic data, providing statistical bounds on decision costs.
LOOCV is often useful for analyzing small, structured experimental designs.
problem The effectiveness of cross-validation in analyzing designed experiments.
method Empirical study comparing LOOCV and other model selection methods.
result LOOCV is often useful in the analysis of small, structured experimental designs.
MMCGAN uses explicit manifold learning to improve GAN performance.
problem GAN mode collapse and unstable training.
method Introduces Minimum Manifold Coding (MMC) as a prior to guide GAN training.
result MMCGAN effectively alleviates mode collapse and stabilizes GAN training.
Distributed machine learning is an approach allowing different parties to learn a model over all data sets without disclosing their own data. In this paper, we propose a weighted distributed differential privacy (WD-DP) empirical risk minimization (ERM) method to train a model in distributed setting, considering differ…
The paper addresses bias in visual recognition models by reweighting observations.
problem Bias in deep neural networks trained on biased image databases.
method Reweighting observations based on known biasing mechanisms to form a nearly debiased estimator.
result The approach can remedy representativeness issues in visual recognition systems.
The study analyzes how wartime controls influenced zaibatsu stock prices in Japan.
problem How wartime economic controls affected zaibatsu stock prices in Japan.
method Developed a four-portfolio asset-pricing model and used a CAPM-AR(p)-SV event-study framework.
result Wartime economic controls influenced stock prices through financing wedges and zaibatsu affiliation.
Recent research on Bitcoin Transaction Networks reveals a growing, sparse, and core-periphery structure.
problem Understanding the evolution of Bitcoin's network structure and user behavior.
method Review of recent results on Bitcoin Transaction Networks, including Address Network, User Network, and Lightning Network.
result Bitcoin Transaction Networks exhibit a core-periphery structure, indicating increasing centralization.
Develops methods for valid and validated confidence sets in multiclass and multilabel prediction.
problem Challenges of typical conformal prediction methods in multiclass and multilabel problems, especially uneven coverage.
method Leverages quantile regression to build methods that always guarantee correct coverage and asymptotically optimal conditional coverage, addressing label interactions with tree-structured classifiers.
result Empirical evaluation suggests more robust coverage of confidence sets.
Improved nuclear cross section fitting with weighted Levenberg-Marquardt method.
problem Challenging optimization in multichannel nuclear cross section data.
method Weighted Levenberg-Marquardt algorithm with Fisher Information Metric.
result More physically consistent fits for raw and smoothed datasets.
Tricks adversarial attacks to target specific classes, improving classifier accuracy.
problem Recent adversarial defense approaches have failed to protect classifiers from untargeted attacks.
method Target Training defense tricks untargeted attacks into targeted attacks on designated classes, then derives the real class.
result 86.2% accuracy for CW-L2 (confidence=0) in CIFAR10, outperforming unsecured classifiers.
Two new undersampling methods improve classification accuracy for imbalanced datasets.
problem Class imbalance and distributional differences in large datasets lead to biased models and poor predictive performance.
method Mutual information-based stratified simple random sampling and support points optimization.
result Empirical results show higher balanced classification accuracy compared to traditional techniques.
WamOL uses PINNs to efficiently calibrate IVS from sparse data.
problem Calibrating time-dependent IVS from sparse market data.
method Physics-Informed Neural Networks (PINNs) with adaptive reweighting.
result WamOL outperforms in calibrating intraday IVS from uneven data.
Success stories of applied machine learning can be traced back to the datasets and environments that were put forward as challenges for the community. The challenge that the community sets as a benchmark is usually the challenge that the community eventually solves. The ultimate challenge of reinforcement learning rese…
In colored graphs, node classes are often associated with either their neighbors class or with information not incorporated in the graph associated with each node. We here propose that node classes are also associated with topological features of the nodes. We use this association to improve Graph machine learning in g…
Study examines how disturbances affect financial returns in Austrian forests.
problem Financial impact of disturbances on timberland returns in Austria.
method Applied probability theory to analyze two management regimes: even-aged and semi-stationary.
result Severe disturbances can lead to a shift from continuous-cover to even-aged forestry, affecting financial sensitivity.
Study shows non-systematic bias in customer satisfaction surveys limits data value.
problem Non-systematic bias in customer satisfaction surveys limits data value.
method Used real customer satisfaction survey data of a large retail bank to show the irreducible error and suggest thoughtful survey design methods.
result A thoughtful survey design can reduce non-systematic error in customer satisfaction surveys.