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.
CRC improves multivariate forecasting accuracy without risking performance degradation.
Proposes a neural network method to correct residual distortions in coordinate transformations.
Hybrid method improves SABR implied volatility approximation.
Neural operators correct PDE residuals to improve BIP solutions.
We provide local expressions for Chern-Weil type forms built from superconnections associated with families of Dirac operators previously investigated in work by S. Scott and later work by S. Scott and the second author. When the underlying fibration of manifolds is trivial, the even degree forms can be interpreted as …
Improved stochastic approximation method reduces residual error.
ProxySHAP approximates Shapley and Banzhaf interactions efficiently.
SA-PEF improves federated learning efficiency by correcting gradient mismatches.
This paper examines the use of a residual bootstrap for bias correction in machine learning regression methods. Accounting for bias is an important obstacle in recent efforts to develop statistical inference for machine learning methods. We demonstrate empirically that the proposed bootstrap bias correction can lead to…
Bias correction needed after deep learning regression training.
Sparse subspace clustering (SSC) using greedy-based neighbor selection, such as matching pursuit (MP) and orthogonal matching pursuit (OMP), has been known as a popular computationally-efficient alternative to the conventional L1-minimization based methods. Under deterministic bounded noise corruption, in this paper we…
TRA detects causal direction from bivariate data using geometric shapes.
Gradient Boosting Machine (GBM) is an extremely powerful supervised learning algorithm that is widely used in practice. GBM routinely features as a leading algorithm in machine learning competitions such as Kaggle and the KDDCup. In this work, we propose Accelerated Gradient Boosting Machine (AGBM) by incorporating Nes…
New diagnostic method detects misspecified models in inverse PDE problems.
Enhances anomaly detection in high dimensions with pretrained networks.
New estimator improves off-policy evaluation for large action spaces.
The paper establishes principles for initializing and designing GNNs with ReLU activations to avoid oversmoothing and correlation collapse.
In this paper, we present NESTA, a specialized Neural engine that significantly accelerates the computation of convolution layers in a deep convolutional neural network, while reducing the computational energy. NESTA reformats Convolutions into batches and uses a hierarchy of Hamming Weight Compressors to …
A method compares AI corrections to a base model for explaining predictions.
New method learns PDE solutions from low-fidelity data.
Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD): the variance in predicted probability of the correct class across iterations of …
This work presents a technique for statistically modeling errors introduced by reduced-order models. The method employs Gaussian-process regression to construct a mapping from a small number of computationally inexpensive `error indicators' to a distribution over the true error. The variance of this distribution can be…
New method uses observational data to improve trial design efficiency.
This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Residual Network. This is supported on single dimensional convolutions computed alongside the time domain, which is a powerful approach to proces…
We identify and study two common failure modes for early training in deep ReLU nets. For each we give a rigorous proof of when it occurs and how to avoid it, for fully connected and residual architectures. The first failure mode, exploding/vanishing mean activation length, can be avoided by initializing weights from a …
Develops EFT for ResNets, revealing limitations of kernel-only approach.
We speed up Gaussian process cross-validation calculations and improve model diagnostics.
We present a general numerical approach for learning unknown dynamical systems using deep neural networks (DNNs). Our method is built upon recent studies that identified the residue network (ResNet) as an effective neural network structure. In this paper, we present a generalized ResNet framework and broadly define res…
Proposes log density gradient to improve reinforcement learning sample complexity.
Reasoning models generate differently based on problem difficulty, not just length.
We derive finite width and depth corrections for the Neural Tangent Kernel (NTK) of ResNets and DenseNets. Our analysis reveals that finite size residual architectures are initialized much closer to the "kernel regime" than their vanilla counterparts: while in networks that do not use skip connections, convergence to t…
Alternative to likelihood-based LSNM model selection, residual independence testing is more robust to noise misspecification.
Random Forests provide interpretable prediction intervals with theoretical guarantees.
Midicoth compresses online probability estimates by correcting prior smoothing biases.
Improved nonparametric regression with debiasing for root-n consistency.
New method improves predictive systems with better theoretical guarantees.
We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and network architecture. They simply amount to at most a matrix inversion and mult…
Corrected moment-based methods improve inference in topic model regression.
This paper introduces and evaluates a novel training method for neural networks: Dual Variable Learning Rates (DVLR). Building on insights from behavioral psychology, the dual learning rates are used to emphasize correct and incorrect responses differently, thereby making the feedback to the network more specific. Furt…
Model analyzes trading frictions in cap-and-trade markets, showing how they interact to affect market effectiveness.
A conservative drifting method improves generative modeling by using KDE gradients, proving convergence rates.
This paper studies the convergence behaviour of dictionary learning via the Iterative Thresholding and K-residual Means (ITKrM) algorithm. On one hand it is proved that ITKrM is a contraction under much more relaxed conditions than previously necessary. On the other hand it is shown that there seem to exist stable fixe…
Generalized Chinese Remainder Theorem (CRT) has been shown to be a powerful approach to solve the ambiguity resolution problem. However, with its close relationship to number theory, study in this area is mainly from a coding theory perspective under deterministic conditions. Nevertheless, it can be proved that even wi…
PIE-PINN estimates elastic properties from noisy, low-res displacement data.
Abstract: Non-residually finite hyperbolic groups imply non-residually finite rigid hyperbolic groups.
Residual finiteness is known to be an important property of groups appearing in combinatorial group theory and low dimensional topology. In a recent work [2] residual finiteness of quandles was introduced, and it was proved that free quandles and knot quandles are residually finite. In this paper, we extend these resul…
In this note, residual finiteness of quandles is defined and investigated. It is proved that free quandles and knot quandles of tame knots are residually finite and Hopfian. Residual finiteness of quandles arising from residually finite groups (conjugation, core and Alexander quandles) is established. Further, residual…
Attenuation correction is an essential requirement of positron emission tomography (PET) image reconstruction to allow for accurate quantification. However, attenuation correction is particularly challenging for PET-MRI as neither PET nor magnetic resonance imaging (MRI) can directly image tissue attenuation properties…