This study examines how topic analysis improves community detection in rating-based social networks.
problem Finding meaningful communities in rating-based social networks.
method The study considers both the contents and topological structures of social networks to find more meaningful communities.
result Topic analysis enhances the identification of meaningful communities in rating-based social networks.
In this paper, we establish a market model for the term structure of forward inflation rates based on the risk-neutral dynamics of nominal and real zero-coupon bonds. Under the market model, we can price inflation caplets as well as inflation swaptions with a formula similar to the Black's formula, thus justify the cur…
The Basel II internal ratings-based (IRB) approach to capital adequacy for credit risk implements an asymptotic single risk factor (ASRF) model. Measurements from the ASRF model of the prevailing state of Australia's economy and the level of capitalisation of its banking sector find general agreement with macroeconomic…
An extension of the Heath--Jarrow--Morton model for the development of instantaneous forward interest rates with deterministic coefficients and Gaussian as well as Lévy field noise terms is given. In the special case where the Lévy field is absent, one recovers a model discussed by D.P.~Kennedy.
The literature on statistical learning for time series assumes the asymptotic independence or ``mixing' of the data-generating process. These mixing assumptions are never tested, nor are there methods for estimating mixing rates from data. We give an estimator for the β-mixing rate based on a single stationary sample…
In this paper, a finite-state mean-reverting model for the short-rate, based on the continuous time Ehrenfest process, will be examined. Two explicit pricing formulae for zero-coupon bonds will be derived in the general and the special symmetric cases. Its limiting relationship to the Vasicek model will be examined wit…
Paper presents a method for estimating long-term PDs with incomplete data.
problem Estimating long-term PDs with limited and incomplete historical data.
method Single risk factor approach for simultaneous calibration of PDs across sub-portfolios.
result Method yields long-term PDs without requiring complete historical data.
Paper proposes hybrid approach for transparent credit scoring models.
problem Lack of transparency in machine learning models limits their use in regulated environments.
method Post-hoc interpretation of black-box models guides feature selection, followed by training glass-box models.
result Reduces feature usage from 106 to 10 while maintaining comparable performance.
Study shows bond market incompleteness with Lévy noise.
problem Incompleteness of forward rate based bond market model driven by Lévy noise.
method Examined the incompleteness of the market when Lévy measure has a density function. Presented theory of stochastic integration and integral representation of local martingales.
result Proven incompleteness of the bond market model under Lévy noise.
New methods reduce private federated learning communication automatically.
problem Reducing communication in private federated learning.
method Automatic compression rate adjustment based on training error, using secure aggregation and differential privacy.
result Provable instance-optimal for mean estimation, achieving favorable compression rates.
New algorithm outperforms existing ones by focusing on mastering rate.
problem Low sample efficiency in learning progress-based algorithms.
method Proposes a new algorithm based on mastering rate.
result Significantly outperforms learning progress-based algorithms.
Deep learning method improves risk assessment for small loan portfolios.
problem Measuring name concentration risk in small loan portfolios.
method Deep learning approach using Monte Carlo simulations with importance sampling.
result New method outperforms existing analytical methods for small portfolios.
New formula classifies product reviews into higher and lower ratings based on sentiment analysis.
problem Lack of research on using sentiment analysis for classifying text into ratings.
method Redefined sentiment proportions as a triangle structure to derive variables for classifying text into higher and lower ratings.
result Proved a dependence exists between sentiments and ratings.
GradaGrad adapts learning rate non-monotonically, overcoming AdaGrad's step size decrease.
problem Fixed learning rate in AdaGrad leads to step size decrease over time.
method Introduces GradaGrad, which grows or shrinks the learning rate based on a different accumulation in the denominator.
result GradaGrad achieves similar convergence rates as AdaGrad and demonstrates non-monotone adaptation.
New sampling and diffusion models methods introduced without density function assumptions.
problem Sampling and diffusion models without regularity assumptions.
method Inspired by reverse diffusion process, novel sampling and diffusion algorithms.
result Explicit convergence rate and dimension-free particle approximation convergence result.
Study on MLE growth rate for stable CIR process, proving consistency and normality.
problem Estimating the growth rate of a stable CIR process from continuous observations.
method Maximum likelihood estimation for a specific type of process.
result Strong consistency and asymptotic normality in subcritical and supercritical cases, asymptotic mixed normality in supercritical, open in critical case.
Develops a new test for comparing two groups' densities, showing minimax optimality.
problem Comparing probability densities between two groups.
method Probabilistic tensor product smoothing spline framework for joint density modeling; penalized likelihood ratio test for interaction testing.
result Proposed test is minimax optimal and outperforms conventional approaches.
This letter assesses model risk in credit capital requirements and finds substantial tail risk.
problem Uncertainty in the probability of default and loss-given-default parameters in credit capital requirements.
method Models estimation risk in a simple way, analyzing two datasets and testing parameter dependency.
result Parameter dependency significantly increases tail risk in capital requirements, requiring substantial increases in regulatory capital.
XNAS optimizes neural architecture search using expert advice theory.
problem Optimizing neural architecture selection with minimal regret.
method Uses prediction with expert advice theory and dynamic architecture wiping.
result Achieves optimal worst-case regret and state-of-the-art results.
FedDuA adapts global learning rate for federated learning.
problem Slow convergence in federated learning due to dataset and parameter space heterogeneity.
method FedDuA uses mirror descent to adaptively select global learning rate based on inter-client and coordinate-wise heterogeneity.
result FedDuA achieves minimax optimal convergence for convex objectives and outperforms baselines in various settings.
Compound Finance optimizes risk metrics for V3 protocol using Chainrisk simulations.
problem Optimizing systemic risks in Compound V3 protocol.
method Millions of Chainrisk simulations to evaluate VaR and LaR, providing parameter adjustments.
result Optimization framework enhances protocol stability.
GRAPE improves RL policy evaluation in noisy environments.
problem Noise in real-world RL environments makes policy evaluation algorithms inefficient or prone to errors.
method GRAPE combines gap-increasing value update operators and off-policy eligibility trace.
result GRAPE is more efficient and noise-tolerant than existing methods.
The Basel II internal ratings-based (IRB) approach to capital adequacy for credit risk plays an important role in protecting the Australian banking sector against insolvency. We outline the mathematical foundations of regulatory capital for credit risk, and extend the model specification of the IRB approach to a more g…
CProp scales learning rate based on past gradient direction.
problem Adaptive learning rate scheduling during training.
method Gradient scaling method based on past gradient conformity.
result Significant gain in training speed on SGD and adaptive methods.
TDprop uses Jacobi preconditioning to improve adaptive optimizers in Deep RL.
problem Improving performance of adaptive optimizers in Deep RL.
method TDprop computes per-parameter learning rates based on Jacobi preconditioning of the TD update rule.
result TDprop matches or exceeds Adam's performance in Deep RL experiments, suggesting Jacobi preconditioning can improve adaptive methods.
In our previous studies we have investigated the structural complexity of time series describing stock returns on New York's and Warsaw's stock exchanges, by employing two estimators of Shannon's entropy rate based on Lempel-Ziv and Context Tree Weighting algorithms, which were originally used for data compression. Suc…
Warm-up improves training by adapting learning rate based on curvature.
problem Improving training efficiency in deep learning models.
method Introducing a curvature condition to explain warm-up, and showing empirically that it leads to faster convergence.
result Adapting learning rate based on curvature condition naturally induces warm-up-like schedule, leading to faster convergence.
Abstract framework for cross-currency interest rate contracts.
problem Handling cross-currency markets with collateral and incompleteness.
method Developed a general HJM framework for abstract market indices.
result Enabled simultaneous description of multiple currency interest rate products.
Deep networks learn sparse hierarchical features without CoD.
problem Overparameterized deep networks struggle with the curse of dimensionality.
method Norm-constrained neural networks for sparse compositional functions.
result Deep networks can learn sparse hierarchical features efficiently.
New measure quantifies contrastive self-supervised learning's generalization ability.
problem Limited theoretical understanding of contrastive self-supervised learning's generalization.
method Defined (σ,δ)-measure to mathematically quantify data augmentation and provide an upper bound for downstream classification error. result Generalization ability is related to alignment of positive samples, divergence of class centers, and concentration of augmented data.
Simple attack bypasses state-of-the-art DNN watermarking.
problem Protecting DNN models from watermark removal attacks.
method Combining imperceptible pattern embedding and spatial-level transformations for a simple yet effective watermark removal.
result Our attack bypasses state-of-the-art watermarking solutions with high success rates.
Study evaluates neural networks for corporate credit rating assessment.
problem Improving machine learning algorithms for credit assessment.
method Analysis of four neural network architectures (MLP, CNN, CNN2D, LSTM) on financial data from energy, financial, and healthcare sectors.
result LSTM architecture consistently outperforms others in predicting corporate credit ratings.
SplitSGD dynamically adjusts learning rate based on stationarity detection.
problem Optimizing learning rates for stochastic optimization.
method SplitSGD uses a simple stationarity detection method to adjust learning rates.
result SplitSGD improves generalization and outperforms other adaptive methods.
Adaptive prediction timing improves healthcare outcomes by predicting patient events at the right frequency.
problem Inconsistent prediction granularity in healthcare models.
method Introduces a novel approach using Bayesian recurrent models and a new aggregation method to adapt prediction frequency based on uncertainty.
result Adaptive prediction timing leads to improved predictive performance, especially in the critical first 12 hours of patient stay.
This study analyzes AdaGrad's stability and convergence in non-convex optimization.
problem Lack of theoretical analysis for AdaGrad in non-convex optimization.
method Novel stopping time-based techniques from probability theory.
result Established stability and derived convergence rates for AdaGrad.
This paper explores how imperfect reward models can improve online RLHF.
problem Sample efficiency in online RLHF from imperfect reward models.
method Identifies policy coverability and proposes TPO algorithm for transfer learning.
result TPO algorithm improves sample efficiency compared to standard online learning.
How to forecast next year's portfolio-wide credit default rate based on last year's default observations and the current score distribution? A classical approach to this problem consists of fitting a mixture of the conditional score distributions observed last year to the current score distribution. This is a special (…
We propose a model for the credit markets in which the random default times of bonds are assumed to be given as functions of one or more independent "market factors". Market participants are assumed to have partial information about each of the market factors, represented by the values of a set of market factor informa…
New bid shading algorithm reduces costs by 55%.
problem Minimizing costs in online advertising auctions.
method Win-rate prediction and surplus maximization using logistic regression.
result 7% more profit for advertisers compared to benchmarks.
Paper addresses identifiability and asymptotics of ODE systems from noisy data.
problem Identifying parameters and causal structure of linear ODE systems from discrete observations.
method Developed sufficient conditions for identifiability, proved consistency and asymptotic normality of NLS estimator, constructed confidence sets, and inferred causal structure.
result Consistent and asymptotically normal parameter estimator for linear ODE systems under mild conditions.
Develops a new model to better predict corporate bond yields.
problem Persistent shifts in interest rates undermine single-regime models.
method Regime-switching generalized CIR model with two-state short-rate process and credit factors.
result The model improves joint curve fit and delivers interpretable probabilities.
Proposes EDESH-SA for better inventory management under uncertainty.
problem Inventory management under uncertainty.
method Ensemble Differential Evolution with simulation-based hybridization and self-adaptation.
result Improves financial performance and optimizes search spaces.
SOLA framework predicts structured outputs with abstention for opinion analysis.
problem Accurate opinion prediction in structured outputs.
method Decomposes problem into structured abstention and prediction, uses asymmetric losses, surrogate regression, and pre-image problem.
result Extends statistical guarantees on excess risk for fine-grained opinion mining.
AdaS adapts SGD learning rate based on knowledge gain metrics.
problem Empirical step-size selection in SGD optimization lacks consistency and insight.
method Introduces AdaS algorithm that adapts SGD learning rate based on knowledge gain metrics.
result AdaS outperforms existing adaptive learning methods in convergence and generalization.
Proposes ADC for cross-domain recommendation balancing user preferences.
problem Users' preferences change across different domains (e.g., social media, e-commerce).
method Designs a neural architecture and cross-domain loss function to adaptively balance user preferences.
result ADC model effectively balances the impact of domains with different complexities.
In this paper we study iterative procedures for stationary equilibria in games with large number of players. Most of learning algorithms for games with continuous action spaces are limited to strict contraction best reply maps in which the Banach-Picard iteration converges with geometrical convergence rate. When the be…
New method AdaMod stabilizes deep neural network training by limiting adaptive learning rates.
problem Adaptive learning rates can produce extremely large values at the start of training, hindering learning.
method AdaMod uses adaptive and momental upper bounds to restrict learning rates dynamically.
result AdaMod eliminates large learning rates and improves training on complex networks.
Predicts Yelp star reviews using deep learning and network structure.
problem Predicting Yelp star reviews based on network structure and features.
method Compared multiple models including deep learning on network and item features.
result Deep learning models combining node-level and network features outperform others.