Paper proposes Gini distance statistics for estimating feature-label dependence.
problem Identifying statistical dependence between features and categorical labels.
method Generalized Gini distance in RKHS for feature-label dependence estimation.
result Gini distance statistics converge faster and have tighter error bounds than distance covariance.
Frequently, acquiring training data has an associated cost. We consider the situation where the learner may purchase data during training, subject TO a budget. IN particular, we examine the CASE WHERE each feature label has an associated cost, AND the total cost OF ALL feature labels acquired during training must NOT e…
Unified model combines GCN and LPA for better node classification.
problem Combining GCN and LPA for improved node classification.
method Unified model that unifies GCN and LPA, learns edge weights and attention weights.
result Unified model outperforms state-of-the-art GCN-based methods in node classification accuracy.
Pharmaceutical targeting is one of key inputs for making sales and marketing strategy planning. Targeting list is built on predicting physician's sales potential of certain type of patient. In this paper, we present a time-sensitive targeting framework leveraging time series model to predict patient's disease and treat…
We revisit the problem of linear regression under a differential privacy constraint. By consolidating existing pieces in the literature, we clarify the correct dependence of the feature, label and coefficient domains in the optimization error and estimation error, hence revealing the delicate price of differential priv…
Prototypical Networks improve multi-label classification accuracy.
problem Multi-label classification with nonlinear label dependencies.
method Formulate multi-label learning as class distribution in a non-linear embedding space. For each label, positive and negative embeddings are compactly distributed. Labels are inferred by measuring the distance to prototype positive or negative embeddings.
result Extensive experiments show improved accuracy compared to state-of-the-art algorithms.
Extreme Multi-label classification (XML) is an important yet challenging machine learning task, that assigns to each instance its most relevant candidate labels from an extremely large label collection, where the numbers of labels, features and instances could be thousands or millions. XML is more and more on demand in…
Classical clustering algorithms typically either lack an underlying probability framework to make them predictive or focus on parameter estimation rather than defining and minimizing a notion of error. Recent work addresses these issues by developing a probabilistic framework based on the theory of random labeled point…
CausalVAE learns causal relationships in VAE models for better data disentanglement.
problem Learning disentanglement of independent factors from observational data.
method CausalVAE framework with a Causal Layer to transform exogenous factors into causal endogenous ones.
result CausalVAE learns semantically interpretable causal representations and accurately identifies their DAG structure.
AP-Calculus offers a new framework for causal inference in Bayesian networks.
problem Causal inference in Bayesian networks with complex architectures.
method Introduces Attribution Projection Calculus (AP-Calculus) to determine causal relationships.
result Proves that for each label, exactly one intermediate node acts as a deconfounder.
Paper compares GCNs and MPNNs, finding GCNs are one step ahead of WL algorithm.
problem Comparing graph convolutional networks (GCNs) and message-passing neural networks (MPNNs).
method Casts GCNs and MPNNs as MPNNs, studies distinguishing power of different architectures.
result GCNs are one step ahead of the Weisfeiler-Lehman (WL) algorithm in distinguishing power.
This paper deals with the unsupervised domain adaptation problem, where one wants to estimate a prediction function f in a given target domain without any labeled sample by exploiting the knowledge available from a source domain where labels are known. Our work makes the following assumption: there exists a non-linea…
We consider a family of problems that are concerned about making predictions for the majority of unlabeled, graph-structured data samples based on a small proportion of labeled samples. Relational information among the data samples, often encoded in the graph/network structure, is shown to be helpful for these semi-sup…
Proposes a new regression method using conditional GANs.
problem Traditional regression methods make strong assumptions about data distribution.
method Uses conditional GANs to learn prediction functions that match training data pairs.
result New method has better representation capabilities and performs well on real-world datasets.
Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited labeled data to improve the prediction performance. We propose a Bayesian transfer…
Proposes SGShift to identify shifted features causing model performance degradation under concept shift.
problem Concept shift leading to miscalibration in ML models across domains.
method SGShift method for identifying sparse set of shifted features using feature selection and statistical tools.
result SGShift identifies shifted features more accurately than baseline methods, requires few samples in the shifted domain, and is robust to complex cases.
Unified meta-learning framework from supervised learning.
problem Difficulty in comparing and evaluating meta-learning approaches.
method Treating meta-learning as supervised learning, reducing algorithms to supervised learning instances.
result Unified framework and improved model performance on few-shot learning.
Self-training avoids spurious features in domain adaptation.
problem Domain shift with large differences between source and target domains.
method Entropy minimization on unlabeled target data, initialized with a source classifier.
result Entropy minimization avoids using spurious features in large domain shifts.
In-context learning solves PU classification without iterative optimization.
problem Binary classification with only labeled positives and unlabeled samples.
method Pretrained transformer (PUICL) that learns from synthetic PU datasets.
result Outperforms four standard PU learning baselines on 20 benchmarks.
A federated method for feature selection in multi-label data.
problem Feature selection in multi-label data for distributed and federated environments.
method Semi-Supervised Federated Multi-Label Feature Selection (SSFMLFS) using fuzzy information measures.
result SSFMLFS outperforms other methods in feature selection for multi-label data in federated settings.
Vamsa tracks data usage in Python scripts for ML models.
problem Automatically tracking data used in ML model training.
method Modular system that extracts provenance from Python scripts.
result Vamsa achieves high precision and recall in tracking data usage.
The most important aspect of any classifier is its error rate, because this quantifies its predictive capacity. Thus, the accuracy of error estimation is critical. Error estimation is problematic in small-sample classifier design because the error must be estimated using the same data from which the classifier has been…
Paper introduces a new method for error estimation in classification tasks with limited data.
problem Challenges in designing accurate classifiers and evaluating their performance with limited training data.
method Introduces a novel Bayesian MMSE estimator for optimal Bayesian transfer learning (OBTL) using Monte Carlo importance sampling.
result Proposed OBTL error estimation scheme outperforms standard methods, especially in small-sample settings.
Painless Activation Steering automates post-training for LMs without manual intervention.
problem Manual post-training methods are time-consuming and labor-intensive.
method Painless Activation Steering (PAS) is a fully automated approach that requires no manual intervention.
result PAS reliably improves performance for behavior tasks but not for intelligence-oriented tasks.
LLM forecasting benchmarks suffer from information leakage, which confounds model performance.
problem LLM forecasting benchmarks suffer from information leakage.
method A retrieval-augmented LLM forecaster observes only decision-time information.
result The full pipeline obtains a median monthly Spearman rank IC of +0.154.
Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on "meta-learning…
New tail dependence measures for stock indices.
problem Measuring tail dependence between financial variables.
method Introducing a new stochastic order and studying monotone tail dependence measures.
result Advantage of new tail dependence measures over classical ones.
Proposes a new dependency function for measuring non-linear relationships.
problem Need for a general-purpose measure of dependency between random variables.
method Revision of ideal properties and proposal of a new dependency function.
result Proposes a new dependency function that meets all desired properties.
The paper explores the relationship between joint mixability and negative dependence structures.
problem Understanding the connection between joint mixability and various negative dependence concepts.
method Analyzes the properties of joint mixes and their relation to negative dependence structures.
result Derives necessary and sufficient conditions for a joint mix to be negatively dependent.
Extend classical theory of affine processes to path-dependent setting
problem Path-dependent affine processes
method Introduce path-dependent coefficients and provide analytic formulas for their Fourier--Laplace transform
result Define path-dependent affine processes through their exponential-affine Fourier--Laplace transform and establish a characterization theorem
Extremal dependence between international stock markets is of particular interest in today's global financial landscape. However, previous studies have shown this dependence is not necessarily stationary over time. We concern ourselves with modeling extreme value dependence when that dependence is changing over time, o…
Forecaster uses graph Transformers to forecast spatial and time-dependent data.
problem Complex spatial and temporal dependencies in data.
method Graph Transformer architecture with sparsification for spatial and temporal dependencies.
result Forecaster significantly outperforms state-of-the-art baselines in taxi demand forecasting.
Predicts financial asset dependencies using spatiotemporal patterns.
problem Complex dependency structures in financial assets for risk mitigation.
method Proposes Asset Dependency Matrix (ADM) and Asset Dependency Neural Network (ADNN) with ConvLSTM for spatiotemporal asset dependency prediction.
result ADNN outperforms baselines in predicting asset dependencies and their applications.
ST-SAN predicts flow with spatial-temporal dependencies using self-attention.
problem Challenges in predicting flow due to spatial-temporal dependencies.
method Spatial-Temporal Self-Attention Network (ST-SAN) that addresses temporal and spatial dependencies.
result Significant improvement in flow prediction accuracy (9% in inflow, 4% in outflow) compared to state-of-the-art methods.
The paper develops methods to price and hedge options in path-dependent stock models.
problem Pricing and hedging options under complex stock models.
method Develops a path-dependent PDE for option pricing and differentiability of path-dependent SDE solutions.
result Provides formulas for option Greeks and differentiability of path-dependent SDE solutions.
New inequalities for learning from graph-dependent data with stability bounds.
problem Learning from dependent data with graph dependency.
method Proved McDiarmid-type concentration inequalities for graph-dependent variables, showed concentration relies on forest complexity.
result Proved stability bounds for learning from graph-dependent data.
Survey on learning with graph-dependent data, deriving new generalization bounds.
problem Traditional i.i.d. data assumption fails in many real-life applications.
method Collect and analyze graph-dependent concentration bounds, derive generalization bounds.
result New generalization bounds for graph-dependent data.
Paper tackles instance-dependent label noise by approximating it with part-dependent noise.
problem Learning with instance-dependent label noise is challenging.
method Approximate instance-dependent label noise with part-dependent noise. Use transition matrices for parts to model noise.
result Method outperforms state-of-the-art approaches for instance-dependent label noise.
Estimating the strength of dependency between two variables is fundamental for exploratory analysis and many other applications in data mining. For example: non-linear dependencies between two continuous variables can be explored with the Maximal Information Coefficient (MIC); and categorical variables that are depende…
In data science, it is often required to estimate dependencies between different data sources. These dependencies are typically calculated using Pearson's correlation, distance correlation, and/or mutual information. However, none of these measures satisfy all the Granger's axioms for an "ideal measure". One such ideal…
Deep signature algorithm for pricing path-dependent options.
problem Pricing path-dependent options with complex payoff functions.
method Extended backward scheme for state-dependent FBSDEs with reflections, incorporating signature layer for path-dependent FBSDEs.
result Convergence analysis of the algorithm with explicit dependence on truncation order and neural network approximation errors.
Study on pairwise counter-monotonicity, a type of negative dependence.
problem Understanding and quantifying extremal negative dependence structures.
method Established stochastic representation and invariance property; showed implications and connections.
result Pairwise counter-monotonicity implies negative association and joint mix dependence.
New measures capture tail dependence and non-exchangeability in financial data.
problem Underestimation of tail dependence and inability to capture non-exchangeable tail dependence.
method Tail copulas and novel tail dependence measures (MTCM, ATCM) are proposed.
result Captures non-exchangeable tail dependence and provides analytical forms for various copulas.
This paper presents a new methodology for clustering multivariate time series leveraging optimal transport between copulas. Copulas are used to encode both (i) intra-dependence of a multivariate time series, and (ii) inter-dependence between two time series. Then, optimal copula transport allows us to define two distan…
Study nearest-neighbor radii under dependent sampling, finding they remain informative.
problem Analyzing nearest-neighbor radii under dependent sampling.
method Consider strong mixing dependent observations, establish distribution-free almost sure convergence and sharp non-asymptotic moment bounds.
result Nearest-neighbor geometry remains informative under dependence sampling.
Study of time-dependent metrics and connections in geometry.
problem Understanding geodesics and connections in time-dependent Riemannian manifolds.
method Examine connections on product manifolds, explore parallel transport, geodesics, and torsion.
result Define the derivative of a one-parameter family of connections.
Estimating the dependency of variables is a fundamental task in data analysis. Identifying the relevant attributes in databases leads to better data understanding and also improves the performance of learning algorithms, both in terms of runtime and quality. In data streams, dependency monitoring provides key insights …
Estimates binary labels from dependent data using Markov Random Fields.
problem Statistical estimation from dependent data across spatial, temporal, and social domains.
method Modeling dependencies as Markov Random Fields and providing efficient estimation algorithms.
result Statistically efficient estimation rates for Ising models from a single sample.