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.
We present PESMO, a Bayesian method for identifying the Pareto set of multi-objective optimization problems, when the functions are expensive to evaluate. The central idea of PESMO is to choose evaluation points so as to maximally reduce the entropy of the posterior distribution over the Pareto set. Critically, the PES…
This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Mark…
Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of features corresponding to the intra-class variation and the angle correspond…
Unified q-learning for mean-field jump-diffusion models with unobservable population distribution.
problem Continuous-time q-learning in mean-field jump-diffusion models with unobservable population distribution.
method Proposed decoupled Iq-function for unified policy evaluation in MFG and MFC problems; unified q-learning algorithm based on test policies and averaged martingale orthogonality condition.
result Unified policy evaluation rule for MFG and MFC problems based on decoupled Iq-function.
The paper proposes methods to extract and analyze individual variable information from complex dependencies.
problem Analyzing and understanding complex dependencies between multiple variables.
method Reversible normalization and iterative dependency reduction to extract individual information, and use it for direct mutual information and multi-feature Granger causality analysis.
result Decoupling of variables to analyze their individual information and direct mutual information transfers.
We investigate probabilistic decoupling of labels supplied for training, from the underlying classes for prediction. Decoupling enables an inference scheme general enough to implement many classification problems, including supervised, semi-supervised, positive-unlabelled, noisy-label and suggests a general solution to…
We consider a class of participation rights, i.e. obligations issued by a company to investors who are interested in performance-based compensation. Albeit having desirable economic properties equity-based debt obligations (EbDO) pose challenges in accounting and contract pricing. We formulate and solve the associated …
We present two instances, L-GAE and L-VGAE, of the variational graph auto-encoding family (VGAE) based on separating feature propagation operations from graph convolution layers typically found in graph learning methods to a single linear matrix computation made prior to input in standard auto-encoder architectures. Th…
LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
problem LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
method Formulate LLM evaluation as a positive-unlabelled learning problem and propose a geometric auditing framework based on Partial Optimal Transport.
result Improved alignment with human preferences, increased robustness to presentation biases, and interpretable confidence estimates.
Reinforcement learning frameworks have introduced abstractions to implement and execute algorithms at scale. They assume standardized simulator interfaces but are not concerned with identifying suitable task representations. We present Wield, a first-of-its kind system to facilitate task design for practical reinforcem…
Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that creates a shared representation space where knowledge can be robustly transferred. …
Stylized facts can be regarded as constraints for any modeling attempt of price dynamics on a financial market, in that an empirically reasonable model has to reproduce these stylized facts at least qualitatively. The dynamics of market prices is modeled on a macro-level as the result of the dynamic coupling of two dyn…
Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in backpropagation algorithm constrains us from updating network layers in parallel and fully l…
Decoupled PFNs improve sequential decision-making by separating epistemic and aleatoric uncertainties.
problem Sequential decision-making requires distinguishing between epistemic uncertainty about latent signals and irreducible aleatoric observation noise.
method Developed a decoupled PFN architecture that uses query-level labels to train separate heads for latent signal and aleatoric noise.
result Empirically, decoupled PFNs mitigate the failure mode of total-variance exploration in noisy and heteroscedastic settings.
DynamicVAE improves disentanglement and reconstruction accuracy without sacrificing one for the other.
problem The inherent trade-off between disentanglement and reconstruction accuracy in VAE models.
method DynamicVAE uses a modified incremental PI controller to dynamically adjust the weight β during training, decoupling disentanglement and reconstruction accuracy.
result DynamicVAE significantly improves reconstruction accuracy while maintaining disentanglement comparable to existing methods.
We investigate the convergence and stability properties of the decoupled extended Kalman filter learning algorithm (DEKF) within the long-short term memory network (LSTM) based online learning framework. For this purpose, we model DEKF as a perturbed extended Kalman filter and derive sufficient conditions for its stabi…
Unsupervised representation learning via generative modeling is a staple to many computer vision applications in the absence of labeled data. Variational Autoencoders (VAEs) are powerful generative models that learn representations useful for data generation. However, due to inherent challenges in the training objectiv…