A new method prioritizes and recycles experiences for better reinforcement learning.
problem Improving reinforcement learning efficiency by prioritizing and recycling experiences.
method Double-prioritized state-recycled (DPSR) experience replay.
result DPSR achieved state-of-the-art results in Atari games, outperforming original and prioritized methods.
Paper predicts recycling bin full events to reduce RVM downtime.
problem Predicting bin full events to increase RVM uptime.
method Hybrid approach combining machine learning and statistical approximation.
result Forecasting leads to less downtime and costs compared to emptying strategies.
The paper analyzes debt recycling strategies for mortgage repayment, revealing complex phases of success and failure.
problem Evaluating the effectiveness of debt recycling strategies compared to standard mortgage repayment.
method Developed a dynamical model to study the time evolution of equity and mortgage balance under various conditions.
result The model identifies four phases: strongly successful, weakly successful, default, and permanent re-mortgaging, with sensitivity to initial conditions.
Model analyzes debt recycling strategies under various fiscal regimes and jurisdictions.
problem Understanding debt recycling dynamics and their impact on repayment times and equity growth.
method Developed a calibrated model incorporating mortgage interest rates, borrowing costs, and tax shields.
result Introducing positive interest rates without tax shields contracts success regions and lengthens repayment times, but tax shields partially reverse these effects.
A new framework for recycling Gaussian process approximations.
problem Efficiently combining multiple Gaussian process approximations.
method Construct variational ensembles using a dictionary of fitted Gaussian processes.
result Framework allows for various tasks and scalability.
Paper proposes recycling model updates in federated learning by exploiting low-rank gradient subspaces.
problem Large parameter transmissions in federated learning.
method Look-back Gradient Multiplier (LBGM) algorithm exploiting low-rank property of gradient subspaces.
result LBGM reduces communication overhead with minimal performance loss.
Framework reuses pre-trained models for data-free transfer learning.
problem Challenges in retrieving source data for model training.
method Model Recycling Framework for parameter-efficient training.
result Makes multi-source data-free supervised transfer learning possible.
A new method for efficient nested Monte Carlo simulations in financial modeling.
problem Computational challenges in nested stochastic modeling for financial risk assessment.
method Sample recycling approach to speed up inner loop estimations.
result Significantly more efficient than traditional techniques.
We propose a scheme for recycling Gaussian random vectors into structured matrices to approximate various kernel functions in sublinear time via random embeddings. Our framework includes the Fastfood construction as a special case, but also extends to Circulant, Toeplitz and Hankel matrices, and the broader family of s…
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past traject…
Monte Carlo methods are essential tools for Bayesian inference. Gibbs sampling is a well-known Markov chain Monte Carlo (MCMC) algorithm, extensively used in signal processing, machine learning, and statistics, employed to draw samples from complicated high-dimensional posterior distributions. The key point for the suc…
AI learns to design chemical processes efficiently.
problem Designing efficient chemical processes.
method Hierarchical reinforcement learning and graph neural networks.
result Quick learning in various decision spaces.
This work improves testing of machine learning model modifications using novel statistical methods.
problem Overfitting and conservative Bonferroni correction when testing multiple model modifications.
method Introduces alpha-recycling and SRGPs to control error rate and approve more beneficial modifications.
result Novel statistical methods approve a higher number of beneficial modifications than previous approaches.
Contrary to the situation with stochastic gradient descent, we argue that when using stochastic methods with variance reduction, such as SDCA, SAG or SVRG, as well as their variants, it could be beneficial to reuse previously used samples instead of fresh samples, even when fresh samples are available. We demonstrate t…
Geometric structure reveals optimal investment and hedging products.
problem Optimal design of investment and hedging products.
method Investigation of geometric structure in risks and returns using a simple formula.
result Duality between hedging and investment with geometric interpretation of rationality.
New probabilistic method speeds up calibration of complex models.
problem Calibrating large-scale differential equation models efficiently.
method Probabilistic approach to computing local sensitivities.
result Significantly reduces computational effort for iterative gradient-based calibration.
NAPP-ERM improves ERM with differential privacy guarantees by iteratively achieving target regularization and delivering strong convexity.
problem Over-regularization in privacy-preserving ERM approaches.
method Noise-Augmented Privacy-Preserving Empirical Risk Minimization (NAPP-ERM) with a dual-purpose l2 regularizer and privacy budget retrieval strategy.
result Mitigates over-regularization and achieves strong convexity through a single regularizer.
Every production-recycling iteration accumulates an inevitable proportion of its matter-energy in the environment, lest the production process itself would be a system in perpetual motion, violating the second law of Thermodynamics. Such high-entropy matter depletes finite stocks of ecosystem services provided by the e…
New heat dispersion laws established for smooth compact manifolds.
problem Understanding heat dispersion in smooth compact manifolds.
method Established new heat dispersion laws through Theorem 1.1 and explored them further with Propositions 3.1 and 3.2.
result New heat dispersion laws for smooth compact manifolds.
Improved nested simulation for financial risk measurement.
problem Efficiently estimating nested risk measures in financial engineering.
method Reusing inner simulation outputs to improve efficiency and accuracy.
result The proposed approach outperforms standard nested simulation and regression methods.
The green area of economy is the key of healthy living. It is necessary to convene economic and ecologic framework to establish a market attentive to drastic reduction of emissions damaging our climate and landscapes in rural areas, to the protection of biological diversity of the planet, to stop producing nuclear wast…
Focusing on the grand-canonical extension of the ordinary restricted Boltzmann machine, we suggest an energy-based model for feature extraction that uses a layer of hidden units with varying size. By an appropriate choice of the chemical potential and given a sufficiently large number of hidden resources the generative…
Matrix completion is a widely used technique for image inpainting and personalized recommender system, etc. In this work, we focus on accelerating the matrix completion using faster randomized singular value decomposition (rSVD). Firstly, two fast randomized algorithms (rSVD-PI and rSVD- BKI) are proposed for handling …
The paper improves SBI for BHMs by diagnosing misspecification and inferring parameters.
problem Model misspecification in Bayesian hierarchical models.
method Two-step framework: latent function diagnosis followed by SBI of target parameters.
result Improved simulation-based inference for complex models without explicit model checking.
New methods accelerate NCGP inference by trading computation for uncertainty.
problem Prohibitively expensive exact inference in NCGPs for large datasets.
method Iterative methods explicitly modeling approximation error, leveraging parallel computing.
result Significant acceleration of posterior inference compared to baselines.
Normalizing flow regression approximates posterior distributions without additional sampling.
problem Bayesian inference with computationally expensive likelihood evaluations.
method Normalizing flow regression (NFR) for offline inference.
result NFR yields a tractable posterior approximation through regression on existing log-density evaluations.
We present a new paradigm for speeding up randomized computations of several frequently used functions in machine learning. In particular, our paradigm can be applied for improving computations of kernels based on random embeddings. Above that, the presented framework covers multivariate randomized functions. As a bypr…
Kernel interpolation speeds up online Gaussian process updates.
problem Efficiently updating Gaussian process posteriors with new data.
method Structured kernel interpolation for constant-time updates.
result Exact inference maintained with constant-time updates.
Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks. Unfortunately, the high cost of generating strong adversarial examples makes standard adversarial training impractical on large-scale problems like ImageNet…
Variational inference provides approximations to the computationally intractable posterior distribution in Bayesian networks. A prominent medical application of noisy-or Bayesian network is to infer potential diseases given observed symptoms. Previous studies focus on approximating a handful of complicated pathological…
This paper improves neural network predictions with early stopping using conformal calibration.
problem Lack of precise statistical guarantees for neural networks trained with early stopping.
method Conformalized early stopping that combines early stopping with conformal calibration.
result Models provide both accuracy and precise inferences without additional data splits.
We propose a variance reduction framework for variational inference using the Multilevel Monte Carlo (MLMC) method. Our framework is built on reparameterized gradient estimators and "recycles" parameters obtained from past update history in optimization. In addition, our framework provides a new optimization algorithm …
The study examines dataset usage patterns in machine learning research.
problem Lack of attention to dataset dynamics in machine learning research.
method Analysis of dataset usage patterns across machine learning subcommunities and time periods (2015-2020).
result Increasing concentration on fewer and fewer datasets, significant adoption from other tasks, and concentration across the field on datasets introduced by elite institutions.
Proposes a method to reduce parallel complexity of MLMC in SGD.
problem Poor scalability of MLMC in SGD on parallel platforms.
method Proposes a delayed MLMC gradient estimator to reduce parallel complexity.
result Proves reduction in average parallel complexity per iteration at the cost of slightly worse convergence rate.
Building models, or maps, of robot environments is a highly active research area; however, most existing techniques construct unstructured maps and assume static environments. In this paper, we present an algorithm for learning object models of non-stationary objects found in office-type environments. Our algorithm exp…
BPN defends against adversarial attacks by generating beneficial perturbations.
problem Adversarial attacks cause deep neural networks to misclassify clean inputs.
method BPN generates beneficial perturbations during training to neutralize future adversarial attacks.
result BPN is robust to adversarial examples and more efficient than classical adversarial training.
DeFi exploits lead to reduced CP spreads, contrary to contagion hypothesis.
problem Vulnerabilities in DeFi destabilize traditional short-term funding markets.
method Analysis of commercial paper spreads and regulatory segmentation.
result DeFi exploits lead to a 'Flight-to-Quality' pattern, narrowing rather than widening CP spreads.
PyKale bridges interdisciplinary ML with Python, enabling accurate predictions.
problem Cross-disciplinary barriers in machine learning.
method Knowledge-aware machine learning on graphs, images, texts, and videos.
result Enables multimodal learning and transfer learning with latest deep learning models.
Robotic clothing manipulation improved with fashion image analysis techniques.
problem Automated identification of clothing categories and landmarks for robotic tasks.
method Training data augmentation methods and rotation invariant convolutions.
result Our approach outperforms state-of-the-art models on unseen datasets.
Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and deploying this method - expensive in terms of extra memory and computation costs; …
Interacting particle methods are increasingly used to sample from complex and high-dimensional distributions. These stochastic particle integration techniques can be interpreted as an universal acceptance-rejection sequential particle sampler equipped with adaptive and interacting recycling mechanisms. Practically, the…
Solving symmetric positive definite linear problems is a fundamental computational task in machine learning. The exact solution, famously, is cubicly expensive in the size of the matrix. To alleviate this problem, several linear-time approximations, such as spectral and inducing-point methods, have been suggested and a…
New samplers improve compositional generation with diffusion models.
problem Improving compositional generation with diffusion models.
method Score-based interpretation, energy-based parameterization, Metropolis-corrected samplers.
result New samplers enable successful compositional generation across various tasks.
Paper analyzes CRL generalization under non-i.i.d. settings, providing bounds for practical data reuse.
problem Limited theoretical understanding of CRL generalization under non-i.i.d. data conditions.
method Inspired by U-statistics, derives generalization bounds for CRL under non-i.i.d. settings.
result Required number of samples scales logarithmically with class covering number.
Improved Monte-Carlo models by constraining mutual information between latent and observable variables.
problem Training density models leads to latent variables being useless.
method Weave tighter Monte-Carlo bounds with mutual information constraints.
result Improved training of models with continuous and discrete latent variables.
Persistent sampling improves SMC efficiency by retaining and reusing particles.
problem High computational costs and particle impoverishment in SMC.
method Persistent sampling (PS) retains and reuses particles from all prior iterations, using multiple importance sampling and resampling from a mixture of historical distributions.
result PS achieves more accurate posterior approximations and lower variance in marginal likelihood estimates without additional likelihood evaluations.
The paper proposes AIS for Bayesian inversion of multioutput signals with covariance estimation.
problem Performing uncertainty analysis of covariance matrices in Bayesian inversion problems for multioutput signals.
method Adaptive Importance Sampling (AIS) scheme, split variables, frequentist approach for noise covariance, prior density over covariance matrix.
result Estimation of model parameters and covariance matrix of noise.
Research quantifies financial exclusion risks in UK, focusing on cash infrastructure and socio-economic factors.
problem Localised financial exclusion in the UK as cash infrastructure declines.
method Developed a composite indicator using various input variables.
result Financial exclusion is more prevalent in deprived communities and affluent areas.