Study shows better dropout prediction from clickstream data in MOOCs.
problem Evaluating predictive models of student success in MOOCs.
method Statistical testing of hypotheses about model performance, focusing on algorithms and feature extraction methods.
result Clickstream-based feature extraction outperforms forum- and assignment-based methods in predicting student dropout.
Condorcet's Jury Theorem has been invoked for ensemble classifiers to indicate that the combination of many classifiers can have better predictive performance than a single classifier. Such a theoretical underpinning is unknown for consensus clustering. This article extends Condorcet's Jury Theorem to the mean partitio…
Study predicts P2P lending platform failures using machine learning.
problem Predicting failures of P2P lending platforms in China.
method Used machine learning models with filter and wrapper methods, forward selection, and backward elimination.
result Identified robust variables for predicting platform failures with high AUC and F1 scores.
GANs have hidden assumptions causing practical issues.
problem GANs' practical performance contradicts theoretical guarantees.
method Proposed an alternative method to avoid these issues.
result Alternative method sidesteps the identified problems.
Purpose - This paper seeks to take a cautionary stance to the impact of the marketing mix on customer satisfaction, via a case study deriving consensus rankings for benchmarking on selected retail stores in Malaysia. Design/methodology/approach - The ELECTRE I model is used in deriving consensus rankings via multicrite…
In manifold learning, algorithms based on graph Laplacians constructed from data have received considerable attention both in practical applications and theoretical analysis. In particular, the convergence of graph Laplacians obtained from sampled data to certain continuous operators has become an active research topic…
Log-ergodic model improves velocity of money prediction.
problem Improving velocity of money prediction for economic control.
method Log-ergodic processes to simulate monetary velocity.
result Log-ergodic model offers superior predictive power.
This paper closely examines theoretical and practical aspects of the widely used discounted cash flows (DCF) valuation method. It assesses its potentials as well as several weaknesses. A special emphasize is being put on the valuation of companies using the DCF method. The paper finds that the discounted cash flow meth…
Heterophily affects GNN robustness; separating ego- and neighbor-embeddings improves defense.
problem The robustness of GNNs to adversarial attacks.
method Formalized relation between heterophily and GNN robustness; empirical analysis; design principles for improved robustness.
result Separating ego- and neighbor-embeddings increases GNN robustness.
Most real life systems have a random component: the multitude of endogenous and exogenous factors influencing them result in stochastic fluctuations of the parameters determining their dynamics. These empirical systems are in many cases subject to noise of multiplicative nature. The special properties of multiplicative…
Paper establishes no-regret property for practical EGO optimization.
problem No theoretical bounds on cumulative regret for practical EGO.
method Introduced practical EGO with a positive nugget, analyzed its regret bounds.
result Practical EGO is a no-regret algorithm with sublinear regret bounds.
New method reconstructs significant parts of training data from neural networks.
problem Understanding and reconstructing training data from neural networks.
method Proposes a novel reconstruction scheme based on recent theoretical results about neural network training.
result Shows that a significant fraction of training data can be reconstructed from neural network parameters.
Clustering research lacks systematic guidance for choosing algorithms.
problem Lack of systematic guidance for clustering algorithm selection.
method Focus on model selection as the most significant challenge.
result Current clustering practices often lead to poor outcomes.
Paper investigates differentiable fuzzy implications and their suitability for learning.
problem Analyzing differentiable fuzzy implications and their suitability for learning.
method Investigates the properties of fuzzy implications in a differentiable setting and introduces a new family of fuzzy implications.
result Various fuzzy implications are unsuitable for differentiable learning, and a new family of fuzzy implications is introduced.
The paper develops no arbitrage results for trajectory based models by imposing general constraints on the trading portfolios. The main condition imposed, in order to avoid arbitrage opportunities, is a local continuity requirement on the final portfolio value considered as a functional on the trajectory space. The pap…
Study provides guarantees for kernel clustering under non-parametric mixtures.
problem Statistical guarantees for kernel-based clustering without strong assumptions.
method Non-parametric mixture models, kernel-based clustering, consistency guarantees.
result Necessary and sufficient separability conditions for consistent clustering recovery.
CDM and CEE differ; accurate CEE isn't needed for CDM.
problem Understanding the difference between CDM and CEE.
method Highlighting the distinctions and implications of CDM and CEE.
result Accurate CEE is not necessary for accurate CDM.
Survey on why deep learning works despite having more parameters than data.
problem Understanding why deep learning algorithms generalize well despite having more parameters than training data.
method Explains the concept of implicit bias and reviews recent research findings.
result Implicit bias is a key factor in deep learning's ability to generalize.
We attempt to explain stock market dynamics in terms of the interaction among three variables: market price, investor opinion and information flow. We propose a framework for such interaction and apply it to build a model of stock market dynamics which we study both empirically and theoretically. We demonstrate that th…
Pruning neural networks adds differential privacy noise, preserving data utility.
problem Achieving differential privacy in neural networks without sacrificing data utility.
method Proving equivalence between pruning and adding differential privacy noise to hidden-layer activations.
result Pruning can be a more effective alternative to adding differential privacy noise for neural networks.
New proof shows coupling-based flows converge linearly to diagonalize data covariance.
problem Understanding convergence of coupling-based normalizing flows to arbitrary data distributions.
method Proved linear convergence rate for whitening of data distribution.
result Coupling-based flows achieve linear convergence to diagonalize data covariance.
TransINT embeds KGs by preserving implication rules, outperforming existing methods.
problem Embedding KGs while preserving relation implications for better access and analysis.
method Isomorphic intersections of linear subspaces with shared parameters for missing facts.
result Significant performance improvement in link prediction and triple classification.
Researchers prove Transformers are Turing-complete and analyze their components.
problem Understanding the computational power and limitations of Transformers.
method Analyzed Turing-completeness of vanilla and modified Transformers, and necessity of components.
result Transformers with positional masking and positional encodings are Turing-complete.
Paper improves sample efficiency of transfer learning in diffusion models.
problem Diffusion models need too much data to train from scratch.
method Assumes shared low-dimensional representation across tasks for improved sample efficiency.
result Sample complexity of target tasks can be reduced with a well-learned representation.
ProbE model improves relational implication detection to 0.8143.
problem Improving inference of relational data to extract more useful information.
method Formal probabilistic model of relational implication using estimators based on empirical distribution.
result ProbE model outperforms existing approaches, achieving 0.8143 AUC on evaluation dataset.
Normal surface theory is a central tool in algorithmic three-dimensional topology, and the enumeration of vertex normal surfaces is the computational bottleneck in many important algorithms. However, it is not well understood how the number of such surfaces grows in relation to the size of the underlying triangulation.…
Two Ricci curvature discretizations correlate in complex networks.
problem Comparing two Ricci curvature definitions for complex networks.
method Empirical comparison of Forman-Ricci and Ollivier-Ricci curvatures.
result Forman-Ricci curvature correlates highly with Ollivier-Ricci curvature in real-world networks.
Paper introduces a new pricing model for Uniswap V3 positions.
problem Valuation of Uniswap V3 liquidity positions.
method Stochastic processes and Martingale Stopping Theorem.
result Model provides significant insights into risk exposure and hedging strategies.
Learning feasibility is undecidable in PAC-learning.
problem Deciding the feasibility of learning a mapping between data and labels.
method Investigating the existence of a test for PAC-learnability.
result No test for PAC-learnability exists, showing undecidability.
The benefits of portfolio diversification is a central tenet implicit to modern financial theory and practice. Linked to diversification is the notion of breadth. Breadth is correctly thought of as the number of in- dependent bets available to an investor. Conventionally applications us- ing breadth frequently assume o…
PAC-Bayes bound requires prior to place mass on high-performing predictors.
problem Explaining generalization in machine learning.
method Analyzing necessary conditions for PAC-Bayes bounds to provide meaningful generalization guarantees.
result Achieving a target generalisation level requires the prior to place sufficient mass on high-performing predictors.
Paper summarizes unsupervised learning challenges for disentangled representations.
problem Unsupervised learning of disentangled representations without inductive biases.
method Theoretical and practical analysis of existing approaches.
result Unsupervised disentanglement is fundamentally impossible without inductive biases.
In recent years, the spectral analysis of appropriately defined kernel matrices has emerged as a principled way to extract the low-dimensional structure often prevalent in high-dimensional data. Here we provide an introduction to spectral methods for linear and nonlinear dimension reduction, emphasizing ways to overcom…
New data improves market impact estimation methods.
problem Improving efficiency of market impact estimation.
method Investigates the use of price trajectory data for market impact estimation.
result Estimation methods using early trade prices outperform established methods asymptotically.
Aggregation defenses improve deep learning models' robustness against data poisoning attacks.
problem Data poisoning attacks manipulate deep learning models with malicious training samples.
method Deep Partition Aggregation, efficiency improvements, data-to-complexity ratio, poisoning overfitting phenomenon.
result Aggregation defenses boost poisoning robustness through the poisoning overfitting phenomenon.
This paper uses neural networks to accurately model competing risks in survival analysis.
problem Ignoring competing risks leads to biased survival estimation in machine learning models.
method The paper introduces constrained monotonic neural networks to model each competing survival distribution.
result The method ensures exact likelihood maximization with reduced computational cost.
We describe many vantage points on the Baire metric and its use in clustering data, or its use in preprocessing and structuring data in order to support search and retrieval operations. In some cases, we proceed directly to clusters and do not directly determine the distances. We show how a hierarchical clustering can …
The aim of this paper is to introduce a method for computing the allocated Solvency II Capital Requirement (SCR) of each Risk which the company is exposed to, taking in account for the diversification effect among different risks. The method suggested is based on the Euler principle. We show that it has very suitable p…
Bayesian models overestimate clusters, but practical summaries can correct this.
problem Bayesian mixture models overestimate the number of clusters.
method Simulations and gene expression data analysis using MCMC summarisation.
result Overestimation is limited in finite samples and can be corrected, but misspecification leads to significant overestimation.
VolTS uses stats & ML to forecast stock market trends based on volatility.
problem Capturing profitable trading opportunities from market dynamics.
method Combines statistical analysis with machine learning; k-means++ clustering, Granger causality test.
result Effective at identifying profitable trading opportunities through volatility clusters and Granger causality.
Extends neural network approximation to probability measures and tree-structured data.
problem Universal approximation of functions on probability measures and tree-structured domains.
method Proof of neural network density in probability measure spaces and Cartesian products.
result Universal approximation theorem for tree-structured domains, including JSON.
Automates RL for LTV in recommender systems.
problem Maximizing future user gains over time.
method Combines RL with recommendation systems, automating state-space representation.
result Automated RL for LTV maximizes user gains over time.
Modern machine learning practices contradict traditional bias-variance theory.
problem Modern machine learning models often fit data perfectly, yet perform well.
method Introducing a 'double descent' curve to reconcile classical and modern practices.
result Increasing model capacity beyond interpolation improves performance.
The paper explores how to extrapolate from limited data points using causal mechanisms.
problem Handling distribution shifts with limited target samples.
method Formulates the extrapolation problem with a latent-variable model embodying the minimal change principle in causal mechanisms, and identifies conditions for identification.
result Theoretical understanding and practical methods for extrapolation without requiring an on-support target distribution.
Trading strategy mimics optimal control with simple heuristic.
problem Maximizing profit in markets with limited optimal control.
method Using the gradient of the Bellman value function as effective microstructure alphas.
result Trading strategy approximates optimal behavior in long-term trades.
The cycling operation endows the super summit set Sx of any element x of a Garside group G with the structure of a directed graph Γx. We establish that the subset Ux of Sx consisting of the circuits of Γx can be used instead of Sx for deciding conjugacy to x in G, yielding a faster and more pr…
Study derives new equation for reserves in non-monotone information scenarios.
problem Modeling reserves in situations where information is not always increasing.
method Infinitesimal approach to derive generalized stochastic Thiele equation.
result New equation allows for information discarding and solves open problems.
Survey of methods to train deep architectures without E2EBP.
problem Training deep architectures without end-to-end backpropagation.
method Modular training, weakly modular hybrids.
result Provably optimal alternatives to E2EBP can match or surpass E2EBP performance.