Study expands multiclass classification models with new rates and partial concept classes.
problem Multiclass classification with a bounded number of labels under various conditions.
method Extends traditional PAC model to distribution-dependent and data-dependent learning rates, characterizes optimal rates for universal and partial concept classes.
result Characterizes three types of learning rates (exponential, linear, arbitrarily slow) for fixed distributions and complexity measures for partial concept classes.
Improves interpretability of neural network intermediate layers by making concept activations more robust and effective.
problem Challenges in interpreting neural network decisions and learning in intermediate layers due to opacity and shared interactions.
method Proposes A-CAV to increase effectiveness and employs Gram-Schmidt process to improve robustness.
result Significant improvement in recall rate of concept images from 18.35% to 76.83% for VGG16, with reduced variance in recall across different random seeds.
Theory extends optimal learning rates without realizability assumption.
problem Agnostic binary classification without realizability assumption.
method Identifies tetrachotomy of optimal rates and combinatorial structures.
result Optimal universal rates for binary classification in agnostic setting.
Classifying streaming data requires the development of methods which are computationally efficient and able to cope with changes in the underlying distribution of the stream, a phenomenon known in the literature as concept drift. We propose a new method for detecting concept drift which uses an Exponentially Weighted M…
Market dynamics redefined using a matching rate concept.
problem Difficulty in measuring Supply and Demand at non-execution prices.
method Proposes a new approach where Supply and Demand are always matched but with varying matching rate.
result Equilibrium state maximizes the matching rate, leading to a practical theory.
Study finds flipped classrooms improve student self-concept, enjoyment, but not exam scores.
problem Evaluating the impact of flipped classrooms on higher education outcomes.
method Double/debiased machine learning (DML) approach to analyze student data.
result No significant positive effects on exam scores, passing rates, or knowledge retention.
Paper explains accrual and mark-to-market valuation for interest rate trades.
problem Understanding the valuation differences between accrual and mark-to-market methods for interest rate trades.
method Comparison of discounted cashflow valuation to spread-based valuation, Taylor series approximation, and deferral concept.
result Simple intuition and mathematical explanation of accrual and mark-to-market adjustments.
Paper explores universal rates of ERM in machine learning.
problem Understanding universal learning rates for ERM.
method Analyzes realizable concept classes and ERM principles.
result Four possible universal learning rates by ERM.
Efron et al. (2001) proposed empirical Bayes formulation of the frequentist Benjamini and Hochbergs False Discovery Rate method (Benjamini and Hochberg,1995). This article attempts to unify the `two cultures' using concepts of comparison density and distribution function. We have also shown how almost all of the existi…
Fast, global, and sensitively reacting to political, economic and social events of any kind, these are attributes that social media like Twitter share with foreign exchange markets. The leading assumption of this paper is that information which can be distilled from public debates on Twitter has predictive content for …
Paper presents adaptive minimax risk classifiers for multidimensional concept drift.
problem Multidimensional concept drift in supervised classification.
method Adaptive minimax risk classifiers (AMRCs) tracking multivariate and high-order distribution changes.
result AMRCs provide computable tight performance guarantees and improve classification.
Algorithm detects concept drift and adapts models in streaming data.
problem Concept drift in streaming data renders models inaccurate.
method Adaptive learning algorithm that detects drifts and reacts to them.
result Risk competitive to an algorithm with perfect drift knowledge.
New method uses data perturbation for loss minimization with theoretical guarantees.
problem Data privacy and irrecoverability.
method Regularized loss minimization with local data perturbation.
result Theoretical guarantees of generalization and convergence rates with perturbed data.
DL-FUMI learns heartbeat patterns from BCG signals for precise heart rate estimation.
problem Estimating precise heart rates from ballistocardiogram signals with uncertainty.
method Multiple instance dictionary learning to learn heartbeat concepts from BCG signals.
result DL-FUMI's heartbeat concept achieves superior performance over comparison algorithms.
Study finds relevance of exchange and inflation rates to economic factors.
problem Determining the relevance of exchange and inflation rates to economic factors.
method Introduced concept of adequacy, established positive relation between exchange and inflation rates and other economic factors.
result Close positive relation found between exchange and inflation rates and other economic factors.
A method for concept-based learning using probabilistic inference and expert rules.
problem Concept-based learning with limited training data.
method Divide images into patches, transform into embeddings, cluster, and use frequentist inference to find concepts.
result FI-CBL outperforms concept bottleneck model in small data scenarios.
LFR detects concept drifts in streaming data without distribution assumptions.
problem Concept drift in data over time reduces model predictive performance.
method Linear Four Rates (LFR) framework for detecting and identifying drifts.
result LFR significantly outperforms benchmark approaches in detecting concept drifts.
This paper studies universal rates of ERM for binary classification under agnostic learning.
problem The challenge of achieving universal rates of ERM for binary classification under agnostic learning.
method The paper explores the agnostic universal rates of ERM for binary classification, revealing three possible rates: e−n, o(n−1/2), or arbitrarily slow. result The paper provides a complete characterization of which concept classes fall into each of the three categories of agnostic universal rates.
Study shows religious fasting affects conception rates in Romania.
problem Understanding how religious fasting affects conception rates in Romania.
method Longitudinal analysis of birth records from 1905 to 2001, econometric models.
result Lent fasting has a more significant effect on conception rates in Eastern Orthodox population.
New method tackles concept shifts in nonparametric regression using robust and adaptive transfer learning.
problem Concept shifts and sample scarcity in target domains hinder nonparametric regression.
method Robust and adaptive transfer learning procedure leveraging fixed bandwidth Gaussian kernels.
result Spectral algorithms with fixed bandwidth Gaussian kernels attain minimax convergence rates for nonparametric regression.
The paper tests semantic importance in opaque models using betting.
problem Precise statistical guarantees for semantic concepts in black-box models.
method Formalizes global and local statistical importance via conditional independence and SKIT.
result Shows effectiveness and flexibility of the framework on various models.
Paper detects and adapts to concept drifts in streaming data.
problem Concept drifts deteriorate classification performance over time.
method Hierarchical Hypothesis Testing (HHT) framework for detection and adaptation.
result HLFR detects and adapts to various concept drift types.
RELARM uses relative PCA attributes and k-means clustering for object rating.
problem Rating objects based on complex parameter vectors.
method Relative PCA attributes, k-means clustering, rating vector projection.
result High approximation to existing rating models (S & P, Moody's, Fitch).
COCA refactors training data to identify and erase unsafe concepts in LLMs.
problem Identifying and erasing unsafe concepts in Large Language Models (LLMs) for safety alignment.
method Concept Concentration (COCA) refactors training data with an explicit reasoning process to identify and erase unsafe concepts.
result COCA significantly reduces both in-distribution and out-of-distribution jailbreak success rates while maintaining strong performance on regular tasks.
For binary classification we establish learning rates up to the order of n−1 for support vector machines (SVMs) with hinge loss and Gaussian RBF kernels. These rates are in terms of two assumptions on the considered distributions: Tsybakov's noise assumption to establish a small estimation error, and a new geometr…
Engel explains why interest rates, exchange rates, and inflation puzzles don't exist.
problem Explaining the canonical form of the interest rates, exchange rates, and inflation puzzles.
method Using the concept of a non-pecuniary liquidity return on assets.
result The forward premium puzzle just does not exist, at least not in its canonical form.
Study on optimal rates for learning algorithms with polynomial eigenvalue decay.
problem Understanding convergence rates of learning algorithms under general source conditions.
method Analyzes Tikhonov regularization and operator monotone index functions in minimax setting.
result Establishes upper convergence rates and minimum possible error for learning algorithms.
A new method selects the best ensemble for concept drift detection.
problem Concept drift detection in data streams.
method Dynamic ensemble selection focusing on decisionspace.
result Highest detection precision and lowest false alarms.
Two-dimensional transition rates improve life insurance reserve calculations.
problem Calculating life insurance reserves with Markov assumptions.
method Introducing two-dimensional forward and backward transition rates.
result Two-dimensional transition rates enable more accurate reserve calculations.
Unified bounds linking compressibility, fractal dimensions, and mutual information.
problem Understanding generalization in stochastic learning algorithms.
method Rate-distortion theory applied to machine learning generalization.
result Unified bounds linking compressibility, fractal dimensions, and mutual information.
This paper tackles robust policy learning under concept drifts, improving upon existing methods.
problem Tackles robust policy learning under concept drifts, improving upon existing methods.
method Develops a doubly-robust estimator and a learning algorithm to maximize policy value within a given policy class.
result The proposed algorithm achieves sub-optimality gap of the order κ(Π)n−1/2, demonstrating substantial improvement over existing benchmarks. New approach uses 'growth' and 'harvesting' concepts to improve deep learning models.
problem Current deep learning models lack transparency and high convergence rates.
method Reconsider neural networks as single-species population dynamics with balanced growth and harvesting rates.
result SGD with balanced growth and harvesting rates outperforms adaptive methods in all three requirements.
New online feature selection method handles streaming data with concept drift.
problem Handling streaming data with concept drift and sparsity.
method Online feature screening method with model adaptation.
result Online screening methods with model adaptation outperform without model adaptation on data streams with concept drift.
Study uncertainty metrics from CNN gradients for deep learning tasks.
problem Uncertainty quantification in deep neural networks.
method Gradient metrics for uncertainty quantification, meta classification of predictions.
result Meta classification accuracy similar to entropy thresholding for CNN predictions.
The paper introduces a new learning model that explains practical aspects of machine learning.
problem Understanding how quickly a concept class can be learned from examples in practical scenarios.
method Introducing a new learning model that considers fixed data sources and varying number of training examples.
result There are only three possible rates of universal learning: exponential, linear, or arbitrarily slow.
The report attempts of apply econophysics concepts to the Eurozone crisis. It starts by examining the idea of conservation laws as applied to market economies. It formulates a measure of financial entropy and gives numerical simulations indicating that this tends to rise. We discuss an analogue for free energy released…
TSPRA integrates topics, sentiment, and user preference for better online review prediction and analysis.
problem Improving online review prediction and sentiment analysis accuracy.
method HDP-based model combining topics, sentiment, and user preference.
result Outperforms state-of-the-art model FLAME in rating prediction and sentiment analysis.
Study kernel density estimation for dynamical systems with unique invariant density.
problem Density estimation for dependent observations from dynamical systems.
method Employing C-mixing to measure dependence, universal consistency and convergence rates are established. result Kernel density estimator is universally consistent and achieves convergence rates under L1-norm and L∞-norm. DARec adapts rating patterns across domains without auxillary info.
problem Cross-domain recommendation challenges.
method Deep domain adaptation model (DARec) that transfers rating patterns.
result Best performance on public datasets.
This work shows how transformers use multi-concept word semantics for efficient in-context learning.
problem Understanding the connection between transformer-based LLMs' multi-concept semantic representation and their innovative in-context learning abilities.
method A concept-based low-noise sparse coding prompt model, leveraging advanced techniques to analyze the exponential convergence of 0-1 loss over non-convex training dynamics.
result Transformers leverage multi-concept word semantics to enable powerful and excellent out-of-distribution in-context learning.
MDDM detects concept drifts in evolving data streams using McDiarmid's inequality.
problem Concept drift in rapidly evolving data streams causes inaccurate models.
method Sliding window with weights, comparing weighted means over time.
result MDDM detects concept drifts with shorter delays and lower false negatives.
Mathematical study of excess growth rate connects info theory with finance.
problem Understanding the excess growth rate in portfolio theory.
method Axiomatic characterization theorems of excess growth rate in terms of relative entropy, Jensen's inequality gap, and logarithmic divergence.
result Established rich connections between information theory and finance.
The paper introduces stiffness as a measure of neural network generalization.
problem Understanding and improving neural network generalization.
method Measuring stiffness through gradient effects on different examples and analyzing its dependencies.
result Stiffness correlates with generalization performance and is influenced by learning rate and data point distance.
New method reduces unfairness in binary classification.
problem Achieving similar false positive and negative rates across two populations.
method Penalizes unfairness to achieve balanced false positive and negative rates.
result Empirically validated approach improves fairness and accuracy.
New method detects when models influence their own drift in real-time data streams.
problem Models can induce concept drift in real-time data streams.
method CheckerBoard Performative Drift Detection (CB-PDD)
result CB-PDD effectively detects performative drift in real-time data streams.
Clarifies interest rate cap rules for loans with unconventional cash flows.
problem Ambiguity in applying interest rate caps to loans with non-conventional internal rate of return (IRR).
method Clarified conventional IRR definition, axiomatized, and extended to all loans.
result Unique extension of interest rate cap rule for all loans, based on net present value test.
Large initial learning rate helps neural nets generalize better.
problem Understanding why large initial learning rates lead to better neural net generalization.
method Developed a proof for a two-layer network and demonstrated with experiments on CIFAR-10.
result Proved that a two-layer network trained with a large initial learning rate and annealing generalizes better than one trained with a small learning rate.
A new concept of confidence in learning is defined and analyzed.
problem Understanding and quantifying trust in learning processes.
method Formal axioms, continuum measures, vector fields, loss functions.
result Confidence can be represented and optimized in learning.