Study explains Graph Convolutional Networks decisions.
problem Difficulty in understanding Graph Network decisions.
method Gradient-based and decomposition-based techniques.
result Sets groundwork for future explainability development.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,932 papers · 148 categories
Trend · papers per month
48 results for “toy dataset”
Toy model study shows resampling/reweighting can improve feature learning in imbalanced classification.
problem Improving feature learning in imbalanced classification problems.
method High-dimensional toy model with replica method, class-wise resampling/reweighting, and simplified model.
result No resampling/reweighting can sometimes give best feature learning performance.
Study evaluates unsupervised disentanglement methods on a toy dataset.
problem Lack of clear disentanglement metrics capturing independent features.
method Empirical evaluation of six unsupervised disentanglement methods on MPI3D dataset.
result Beta-TCVAE outperforms other methods in metrics, but not in disentanglement quality.
Boxhead dataset tests autoencoder disentanglement in hierarchical data.
problem Evaluate disentanglement in hierarchical data.
method Introduced Boxhead dataset with hierarchically structured factors, evaluated autoencoder models.
result Hierarchical models outperform single-layer VAEs in disentangling factors.
Paper develops a dual formulation for PCA in Hilbert spaces.
problem Characterizing probabilistic PCA in Hilbert spaces.
method Dual formulation for probabilistic PCA in Hilbert spaces.
result Generative framework for kernel methods developed.
FSPool improves set prediction accuracy and convergence.
problem Set prediction models struggle with simple datasets due to the responsibility problem.
method Featurewise sort pooling to construct a permutation-equivariant auto-encoder.
result FSPool improves reconstructions and representations on various datasets.
MDP Playground tests RL agents across various dimensions for better understanding and debugging.
problem Understanding and debugging reinforcement learning agents across diverse environments and dimensions.
method Controlled testbed with adjustable dimensions for different RL challenges.
result Insights into agent performance and interaction with various dimensions.
Greedy selection works well in a toy model of independent increments.
problem Iterative selection of maximum-value processes from i.i.d. stochastic processes.
method Fixed greedy selection at each stage.
result Optimal strategy is greedy selection under independent increments.
Generalizing semi-supervised generative adversarial networks to regression using feature contrastingcs.LG
In this work, we generalize semi-supervised generative adversarial networks (GANs) from classification problems to regression problems. In the last few years, the importance of improving the training of neural networks using semi-supervised training has been demonstrated for classification problems. We present a novel …
Paper introduces ToyADMOS dataset for detecting anomalous machine sounds.
problem Lack of large-scale datasets for ADMOS anomaly detection.
method Collected anomalous sounds of miniature machines by deliberate damage.
result Released dataset includes over 180 hours of normal and 4,000 anomalous sounds.
Toy Model for Large Non-Symmetric Random Matricesphysics.data-an
Non-symmetric rectangular correlation matrices occur in many problems in economics. We test the method of extracting statistically meaningful correlations between input and output variables of large dimensionality and build a toy model for artificially included correlations in large random time series.The results are t…
Study compares ZBDT model to BDT for financial derivatives valuation.
problem Valuation of financial derivatives under catastrophic events.
method Introduced Zero Black-Derman-Toy (ZBDT) model with jumps to zero interest rate.
result ZBDT model better matches financial slowdown risk.
The paper briefly introduces multiple classifier systems and describes a new algorithm, which improves classification accuracy by means of recommendation of a proper algorithm to an object classification. This recommendation is done assuming that a classifier is likely to predict the label of the object correctly if it…
Learning with Physical Constraintsphysics.flu-dyn
Three physics-constrained regression exercises for image velocimetry and turbulence modeling.
problem Image velocimetry and turbulence modeling challenges.
method Physics-constrained regression exercises implemented as toy problems.
result Python codes provided for all exercises.
Modified BDT model includes zero rate jumps for crisis risk.
problem Quantify risk of future crises in bond prices and derivatives.
method Modified BDT tree model with zero rate jumps, modified algorithms.
result Calibrated tree models show different option prices and volatilities.
EGFs use ergodicity to simplify generative flows for easier training and imitation learning.
problem Challenges in training generative flows, especially in continuous settings and for imitation learning.
method EGFs leverage ergodicity to build simple flows with universality guarantees and tractable FM loss. They introduce a KL-weakFM loss for IL training without a separate reward model.
result EGFs simplify generative flow training and enable effective imitation learning.
New model learns function distributions from datasets.
problem Learning function distributions from datasets.
method Functional Neural Processes (FNPs) model distributions over functions by learning a graph of dependencies on top of latent representations.
result FNPs offer competitive predictions and more robust uncertainty estimates compared to baselines.
Trading behavior and excess volatility in toy marketscond-mat.stat-mech
We study the relation between the trading behavior of agents and volatility in toy markets of adaptive inductively rational agents. We show that excess volatility, in such simplified markets, arises as a consequence of {\em i)} the neglect of market impact implicit in price taking behavior and of {\em ii)} excessive re…
Deep Curvature Suitestat.ML
Deep Curvature Suite offers a PyTorch package for neural network curvature analysis.
problem Insufficient use of curvature information in neural networks.
method Implementation of Lanczos algorithm for neural network curvature analysis.
result Our package outperforms existing methods for similar purposes.
Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexitycs.LG
Accurate and automated detection of anomalous samples in a natural image dataset can be accomplished with a probabilistic model for end-to-end modeling of images. Such images have heterogeneous complexity, however, and a probabilistic model overlooks simply shaped objects with small anomalies. This is because the proba…
A new algorithm improves efficiency in selecting examples for deep learning.
problem Efficiently choosing multiple examples to mark up for deep learning on large datasets.
method Large BatchBALD algorithm, approximating BatchBALD with reduced computational complexity.
result Comparable quality in selection while significantly reducing computation time, especially for large batches.
Paper tackles robust classification under class-dependent domain shift.
problem Class-dependent domain shift in machine learning.
method Defined a simple optimization problem with an information theoretic constraint and solved it using neural networks.
result Demonstrated that the proposed method can learn robust classifiers that generalize well to unseen domains.
In this paper, we propose a novel domain adaptation method that can be applied without target data. We consider the situation where domain shift is caused by a prior change of a specific factor and assume that we know how the prior changes between source and target domains. We call this factor an attribute, and reformu…
Method combines LD and Fermat Distance for neural network uncertainty.
problem Measuring uncertainty in neural network predictions.
method Statistical Depth (LD) combined with Fermat Distance.
result Effective uncertainty estimation without impacting original model performance.
Improved outlier detection in hierarchical Gaussian Processes using Wasserstein-2 kernels.
problem Outlier detection limitations in stacked Gaussian Processes.
method Proposed a hybrid kernel combining Euclidean and Wasserstein-2 distances, emphasizing variance in Wasserstein-2 computations.
result Improved performance and enhanced out-of-distribution detection on various datasets.
Invertible DenseNetscs.LG
Invertible DenseNets improve model efficiency and performance.
problem Improving model efficiency and performance in neural networks.
method Enforcing invertibility in DenseNets by satisfying the Lipschitz constraint and proposing a learnable concatenation.
result i-DenseNets outperform Residual Flows in negative log-likelihood on various datasets.
TOLD++ improves convergence of diffusion models by critically damping the forward transition matrix.
problem Improving the convergence of Denoising Diffusion Probabilistic Models.
method Critically damping the Third-Order Langevin Dynamics (TOLD) forward transition matrix using eigen-analysis.
result TOLD++ converges faster than TOLD, verified on toy and real datasets.
Unsupervised clustering can reproduce categorization systems if features and metrics are correctly selected.
problem Reproducing expert-provided categorization systems using unsupervised clustering.
method Investigated using toy datasets and real-world fund categorization. Used appropriate feature selection and a supervised Random Forest-based distance metric.
result Unsupervised clustering can reproduce ground truth classes if features and metrics are correctly selected.
Clinical diagnostic decision making and population-based studies often rely on multi-modal data which is noisy and incomplete. Recently, several works proposed geometric deep learning approaches to solve disease classification, by modeling patients as nodes in a graph, along with graph signal processing of multi-modal …
FedGAN trains GANs across distributed data sources with reduced communication.
problem Training GANs across non-independent data sources with privacy and communication constraints.
method FedGAN uses local generators and discriminators synced via an intermediary, proving convergence under standard assumptions.
result FedGAN converges and performs similarly to general distributed GANs with reduced communication complexity.
A novel unsupervised domain adaptation method using hierarchical optimal transport.
problem Unsupervised domain adaptation between source and target domains.
method Hierarchical optimal transport, leveraging class labels for structure formation in the source domain and learning probability measures in the target domain.
result The proposed HOT-DA method outperforms state-of-the-art approaches on various datasets.
New metrics assess disentanglement in generative models.
problem Measuring disentanglement in generative models is challenging.
method Introduces manifold entropic metrics based on information theory.
result Ranking of model architectures and training procedures.
In graph-based active learning, algorithms based on expected error minimization (EEM) have been popular and yield good empirical performance. The exact computation of EEM optimally balances exploration and exploitation. In practice, however, EEM-based algorithms employ various approximations due to the computational ha…
SE(3)-Transformers maintain equivariance for 3D data under rotations and translations.
problem Ensuring stable and predictable performance in 3D data under transformations.
method Introducing a self-attention module that is equivariant under continuous 3D roto-translations.
result The SE(3)-Transformer outperforms non-equivariant and non-attention models on real-world datasets.
A study on -GANs proving convergence and estimation guarantees.
problem Analyzing the convergence and estimation guarantees of -GANs.
method Proved a correspondence between -GANs and -divergences, and provided estimation bounds.
result Estimation bounds indicate diverse GAN behavior as a function of .
Defending Diffusion Models Against Membership Inference Attacks via Higher-Order Langevin Dynamicscs.LG
Paper defends diffusion models from membership inference attacks using Langevin dynamics.
problem Defending diffusion models against membership inference attacks.
method Uses critically-damped higher-order Langevin dynamics with auxiliary variables.
result Demonstrates improved resistance to membership inference attacks through theoretical investigation and validation.
DSoftKI scales GP regression with full derivative observations.
problem Efficiently fitting and predicting full derivative observations in Gaussian Processes.
method Extends SoftKI by using local temperature vectors for interpolation, enabling encoding of local directional sensitivity.
result DSoftKI achieves accurate predictions and scales to larger datasets with full derivative observations.
PropEn uses matching to create a larger dataset for efficient design optimization.
problem Limited data and complex landscapes in scientific applications.
method PropEn uses a matching approach to implicitly guide design without a discriminator.
result PropEn efficiently approximates the gradient of property improvement within the data distribution.
A toy model shows how locality can emerge in the universe's Hamiltonian and initial state.
problem Understanding the emergence of locality in the universe's Hamiltonian and initial state.
method A loss functional is minimized by gradient descent to find a tensor product structure.
result Local structure emerges in the universe's Hamiltonian and initial state through spontaneous symmetry breaking.
Reducing Selection Bias in Counterfactual Reasoning for Individual Treatment Effects Estimationcs.LG
Reduces selection bias in estimating individual treatment effects.
problem Selection bias in counterfactual reasoning.
method Auto-encoder with regularized loss based on Pearson Correlation Coefficient.
result Improves performance in estimating individual treatment effects.
New PAC-Bayesian bound improves generalization performance.
problem Improving generalization bounds for learning algorithms.
method Developed a new PAC-Bayesian generalization bound using a Bernstein-like inequality.
result The new bound consistently outperforms existing bounds and converges faster under certain conditions.
Semi-supervised learning objectives as log-likelihoods in a generative model of data curationstat.ML
We explain SSL objectives as log-likelihoods in a data curation model.
problem Lack of understanding of SSL objectives as log-likelihoods.
method Formulate SSL objectives as a log-likelihood in a generative model of data curation.
result SSL methods can be understood as lower-bounds on a principled log-likelihood.
This is an extended write-up of a talk given in April, 1993 in honor of Raoul Bott's 70th birthday. We first illustrate how some traditional topological and geometric invariants obey ``gluing laws'' inspired by those in classical and quantum field theory. Here we discuss characteristic numbers, particularly the Euler n…
Wasserstein Discriminant Analysis (WDA) is a new supervised method that can improve classification of high-dimensional data by computing a suitable linear map onto a lower dimensional subspace. Following the blueprint of classical Linear Discriminant Analysis (LDA), WDA selects the projection matrix that maximizes the …
Python package for estimating intrinsic dimensionality of datasets.
problem Estimating intrinsic dimensionality for machine learning applications.
method Implementation of various intrinsic dimension estimators in Python.
result Benchmarking of ID estimation methods on real and synthetic data.
New method for initializing RBM weights without datasets.
problem No dataset-free weight-initialization for RBMs.
method Statistical mechanical analysis to derive Gaussian distribution with optimized standard deviation.
result Optimal weight initialization improves learning efficiency in RBMs.
New method corrects correlation bias in feature importance.
problem Correlations between features in high-dimensional data bias statistical and machine learning models.
method Pairwise Permutation Algorithm (PPA)
result PPA corrects correlation bias, identifying biological relevant biomarkers.
Handling correlated and repeated measurements with the smoothed multivariate square-root Lassostat.ML
Sparsity promoting norms are frequently used in high dimensional regression. A limitation of such Lasso-type estimators is that the optimal regularization parameter depends on the unknown noise level. Estimators such as the concomitant Lasso address this dependence by jointly estimating the noise level and the regressi…