We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms share important traits with model-based approaches, including the ability to plan…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “replay-based approaches”
We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class. We compare conditional replay to another replay-based continual learning paradigm (which we term "marginal rep…
D-CBRS manages memory for continual learning by accounting for intra-class diversity.
problem Forgetting in continual learning, especially with class-imbalanced data.
method D-CBRS introduces a novel approach to store instances in memory, considering intra-class diversity.
result D-CBRS outperforms existing methods on data sets with intra-class diversity.
CLOPS improves deep learning for continuous physiological data.
problem Deep learning struggles with streaming, multi-sensor clinical data.
method CLOPS is a replay-based continual learning strategy.
result CLOPS outperforms state-of-the-art methods in continual learning scenarios.
Paper proposes a new method to select memory data for online class-incremental learning.
problem Selecting which buffered images to replay for online class-incremental learning.
method Adversarial Shapley value scoring method to preserve latent decision boundaries.
result Proposed ASER method provides competitive or improved performance compared to state-of-the-art methods.
Develops a framework for continual learning in anomaly detection.
problem Deterioration of monitoring performance due to new defect categories.
method Pseudo replay-based class incremental learning with oversampling.
result Enhanced monitoring performance and flexibility in model architecture.
This project combines recent advances in experience replay techniques, namely, Combined Experience Replay (CER), Prioritized Experience Replay (PER), and Hindsight Experience Replay (HER). We show the results of combinations of these techniques with DDPG and DQN methods. CER always adds the most recent experience to th…
Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the -return difficult in this context. In particular, off-policy methods that utilize experience replay remain problematic because their random sampling of minibatch…
La-MAML improves fast online continual learning with a look-ahead approach.
problem Fast online continual learning with limited model capacity.
method Optimisation-based meta-learning with look-ahead and episodic memory.
result Superior performance on visual classification benchmarks.
CAM-GAN improves GANs for continual learning with efficient feature map transformations.
problem Efficient continual learning for GANs with reduced parameter growth.
method Designing and leveraging parameter-efficient feature map transformations, including global and task-specific parameters, residual bias, and Fisher information matrix.
result Significantly improved model performance and high-quality samples with fewer parameters.
This research tackles imbalanced continual learning with a new sampling strategy.
problem Long-tailed distribution in multi-label datasets.
method Partitioning Reservoir Sampling (PRS) for balanced knowledge of head and tail classes.
result The proposed PRS strategy maintains a balanced knowledge of both head and tail classes.
Neural network tackles continual learning with neuromodulation and local error signals.
problem Catastrophic forgetting in continuous learning.
method Biologically-inspired neural architecture with local learning and neuromodulation, combined with transfer metalearning.
result Superior performance in continual learning tasks compared to other approaches.
The paper improves reinforcement learning stability and efficiency with a new theoretical framework.
problem Stability and efficiency in reinforcement learning, especially in data-scarce scenarios.
method Theoretical framework using resampled - and -statistics to model experience replay, applied to policy evaluation and kernel ridge regression.
result Significant improvements in stability and efficiency, particularly in data-scarce scenarios.
ER-GNN uses experience replay to prevent GNNs from forgetting previous tasks.
problem Catastrophic forgetting in GNNs when learning multiple tasks sequentially.
method Experience Replay framework to store and replay knowledge from previous tasks.
result ER-GNN effectively mitigates catastrophic forgetting in GNNs.
SynthER uses generative models to augment limited RL experience.
problem Limited data for reinforcement learning agents.
method SynthER leverages diffusion models to generate synthetic experience data.
result SynthER significantly improves sample efficiency and training of RL agents.
Geometric approach combines asset returns and investor views for better portfolio optimization.
problem Optimizing portfolios with investor-specific views.
method Generalized Wasserstein barycenter (GWB) to integrate statistical asset returns and investor views.
result The geometric approach offers more flexibility and rewards for correct investor views.
Paper proposes an alternative method to price American options using HJM approach.
problem Price American options efficiently and accurately.
method Utilizes HJM technique to model term structure of volatility for equity markets.
result Proposes a new value function, stopping criteria, and stopping time for American options.
We study inference and learning based on a sparse coding model with `spike-and-slab' prior. As in standard sparse coding, the model used assumes independent latent sources that linearly combine to generate data points. However, instead of using a standard sparse prior such as a Laplace distribution, we study the applic…
Quantum machine learning: Adiabatic quantum SVM outperforms classical methods.
problem Training support vector machines efficiently on large datasets.
method Adiabatic quantum computing for SVM training.
result Quantum approach outperforms classical methods in accuracy and scalability.
We develop a semi-analytic approach to the valuation of auto-callable structures with accrual features subject to barrier conditions. Our approach is based on recent studies of multi-assed binaries, present in the literature. We extend these studies to the case of time-dependent parameters. We compare numerically the s…
Two ML approaches learn local volatility surfaces from option prices, with GP being arbitrage-free.
problem Interpolating European vanilla option prices to create a local volatility surface.
method Gaussian process regression and neural net with arbitrage penalties.
result GP approach is arbitrage-free and yields best out-of-sample calibration error.
This paper critiques the Standardized Measurement Approach (SMA) for operational risk and recommends maintaining Advanced Measurement Approach (AMA).
problem Weaknesses and failures of the Standardized Measurement Approach (SMA) in operational risk.
method Critical review and analysis of SMA and AMA approaches.
result SMA is unstable, insensitive to risk, and implicitly related to systemic risk in the banking sector.
Distributed Acoustic Sensing (DAS) using fiber optic cables is a promising new technology for pipeline monitoring and protection. In this work, we applied and compared two approaches for event detection using DAS: Classic machine learning approach and the approach based on image processing and deep learning. Although w…
A new Euclidean approach reveals the pentagram map's beauty.
problem Exploring the pentagram map through classical geometry.
method Introducing an alternative Euclidean approach.
result Demonstrates the pentagram map's elegance through classical geometry.
Two approaches extend knowledge distillation to Gaussian Processes, showing relationships to existing methods.
problem Applying knowledge distillation to Gaussian Processes for regression and classification.
method Data-centric and distribution-centric approaches to extend distillation to GPR and GPC.
result Distribution-centric approach for GPC approximately corresponds to data duplication and scaling.
We discuss the relative merits of optimistic and randomized approaches to exploration in reinforcement learning. Optimistic approaches presented in the literature apply an optimistic boost to the value estimate at each state-action pair and select actions that are greedy with respect to the resulting optimistic value f…
Classical approaches for approximate inference depend on cleverly designed variational distributions and bounds. Modern approaches employ amortized variational inference, which uses a neural network to approximate any posterior without leveraging the structures of the generative models. In this paper, we propose Amorti…
Online boosting method improves weak to strong learner.
problem Online learning of weak to strong learner.
method Extends batch GentleAdaBoost to online approach with line search.
result Online boosting performs better than other methods.
Predicting potential credit default accounts in advance is challenging. Traditional statistical techniques typically cannot handle large amounts of data and the dynamic nature of fraud and humans. To tackle this problem, recent research has focused on artificial and computational intelligence based approaches. In this …
In this paper, we present a new wrapper feature selection approach based on Jensen-Shannon (JS) divergence, termed feature selection with maximum JS-divergence (FSMJ), for text categorization. Unlike most existing feature selection approaches, the proposed FSMJ approach is based on real-valued features which provide mo…
Two new methods for option pricing without or with a riskless asset.
problem Traditional option pricing methods require a riskless asset and may not be market-complete.
method Develops two approaches: one without a riskless asset and one with.
result Both methods produce the same option prices as classical approaches.
An extendable, integrated, and dynamic approach to forecasting and stress-testing credit riskq-fin.CP
An integrated and extendable approach for stress-testing loan portfolios
problem Stress-testing loan portfolios
method Simulate completed portfolios, generate uncertain cash flow history, compute credit risk metrics
result Enhanced stress-testing practices within any bank
Bayesian symbolic regression automates model discovery from data.
problem Learning closed-form mathematical models from data using heuristic methods.
method Probabilistic approach to symbolic regression, connecting to information theory and statistical physics.
result Probabilistic approach provides model plausibility and performance guarantees.
New approach interprets Nyström for kernel machines with geometric insight.
problem No comparative study over Nyström-based kernel machine approaches.
method Developed a new approach with geometric interpretation, showing equivalence to existing methods.
result Proposed approach offers insights into approximation errors and accuracy.
Common Representation Learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, is receiving a lot of attention recently. Two popular paradigms here are Canonical Correlation Analysis (CCA) based approaches and Autoencoder (AE) based approaches. CCA based approaches learn …
Two approaches detect EV charging patterns at stations.
problem Identify charging patterns at electric vehicle charging stations.
method Two approaches: rule-based and hierarchical clustering.
result Hierarchical clustering revealed unexpected charging patterns.
The floating body approach to affine surface area is adapted to a holomorphic context providing an alternate approach to Fefferman's invariant hypersurface measure.
We review classical approaches to the problem of isometrically embedding a Riemannian surface into Euclidean 3-space, including coordinate-based approaches exposited by Darboux and Eisenhart, as well as the moving-frames based approaches advocated by Cartan. In particular, the first approach involves reducing the probl…
Paper evaluates CNN-based facial landmark detection methods.
problem Evaluate characteristics and performance of CNN-based facial landmark detection methods.
method Divided into regression and heatmap approaches, investigated using a hybrid loss function and discrimination network.
result Proposed model outperforms other models in all tested datasets.
This paper provides a comprehensive benchmark and taxonomy for certifiably robust DNN defenses.
problem Certifiably robust defenses against adversarial attacks for deep neural networks.
method Taxonomy and benchmark of certifiably robust approaches.
result First comprehensive benchmark of certifiably robust approaches on different datasets.
VB approach for dynamic network models improves efficiency and accuracy.
problem Estimating dynamic network models in large-scale systems.
method Variational Bayesian inference for network autoregression.
result VB approach detects proper active structures and achieves similar or better accuracy.
New approach for prudent risk evaluation using model aggregation.
problem Risk evaluation and optimization under uncertainty.
method Model Aggregation (MA) approach based on stochastic dominance.
result Produces robust risk evaluation and distributional models.
Study proposes a new approach for deep hedging using artificial market simulations.
problem Challenges in selecting the best model for underlying asset simulations in deep hedging.
method Proposes artificial market simulations to replicate financial market stylized facts.
result Achieves similar performance to traditional approaches without mathematical finance models.
Some of recent developments, including recent results, ideas, techniques, and approaches, in the study of degenerate partial differential equations are surveyed and analyzed. Several examples of nonlinear degenerate, even mixed, partial differential equations, are presented, which arise naturally in some longstanding, …
We compare several approaches to learn an Optimal Map, represented as a neural network, between probability distributions. The approaches fall into two categories: ``Heuristics'' and approaches with a more sound mathematical justification, motivated by the dual of the Kantorovitch problem. Among the algorithms we consi…
The Effect of Optimization Methods on the Robustness of Out-of-Distribution Detection Approachescs.LG
This paper examines how optimization methods affect the reliability of detecting inputs outside a model's training distribution.
problem The unreliability of deep neural networks on out-of-distribution inputs.
method Analysis of optimization methods' impact on OOD detection approaches.
result Optimization methods significantly influence the robustness of OOD detection approaches.
Deep Neural Networks have shown tremendous success in the area of object recognition, image classification and natural language processing. However, designing optimal Neural Network architectures that can learn and output arbitrary graphs is an ongoing research problem. The objective of this survey is to summarize and …
In this paper, we propose three approaches for the estimation of the Tucker decomposition of multi-way arrays (tensors) from partial observations. All approaches are formulated as convex minimization problems. Therefore, the minimum is guaranteed to be unique. The proposed approaches can automatically estimate the numb…