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.
New algorithm reduces performance loss in IRL with mismatched transition dynamics.
This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix.…
SAEs struggle with curved activation manifolds, revealing layer-dependent scaling laws.
The paper addresses score-mismatched diffusion models and zero-shot conditional samplers.
Paper identifies objective mismatch in MBRL, affecting control task performance.
Ensemble decoders to capture latent space topology in deep generative models.
BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
New method addresses error bounds for PnP-ULA under mismatched models.
Paper addresses linear regression with partially mismatched data using local search with theoretical guarantees.
PACMAN provides bounds for classification tasks considering accuracy vs. negative log-loss mismatch.
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution. In this paper, we demonstrate effectiveness of 'mismatched' unlabeled stimulus to perform KD for image classification networks. For illustration, we consider scenarios where this is a comp…
Study on LMMSE estimation with model mismatch, quantifying MSE trade-offs.
Model explains optical illusions using geometric sub-Riemannian geodesics.
Bayesian models for networks are often misspecified, leading to overconfident inference.
Supervised learning based on a deep neural network recently has achieved substantial improvement on speech enhancement. Denoising networks learn mapping from noisy speech to clean one directly, or to a spectrum mask which is the ratio between clean and noisy spectra. In either case, the network is optimized by minimizi…
Recently, there has been significant interest in linear regression in the situation where predictors and responses are not observed in matching pairs corresponding to the same statistical unit as a consequence of separate data collection and uncertainty in data integration. Mismatched pairs can considerably impact the …
Ensemble models improve prediction calibration for mismatched distributions.
The dictionary-aided sparse regression (SR) approach has recently emerged as a promising alternative to hyperspectral unmixing (HU) in remote sensing. By using an available spectral library as a dictionary, the SR approach identifies the underlying materials in a given hyperspectral image by selecting a small subset of…
Empirical study compares finite- and infinite-width BNNs, revealing performance differences under model mismatch.
Transformer model improves asset allocation by unifying forecasting and optimization.
We characterize the performance of sequential information guided sensing, Info-Greedy Sensing, when there is a mismatch between the true signal model and the assumed model, which may be a sample estimate. In particular, we consider a setup where the signal is low-rank Gaussian and the measurements are taken in the dire…
The performance of automatic speech recognition (ASR) systems can be significantly compromised by previously unseen conditions, which is typically due to a mismatch between training and testing distributions. In this paper, we address robustness by studying domain invariant features, such that domain information become…
Many sleep studies suffer from the problem of insufficient data to fully utilize deep neural networks as different labs use different recordings set ups, leading to the need of training automated algorithms on rather small databases, whereas large annotated databases are around but cannot be directly included into thes…
New scheme optimizes BMI through probabilistic and geometric shaping.
Introduces optimization geometrodynamics for dynamic geometric optimization.
In this study, we consider classification problems based on neural networks in data-imbalanced environment. Learning from an imbalanced data set is one of the most important and practical problems in the field of machine learning. A weighted loss function based on cost-sensitive approach is a well-known effective metho…
Most of the existing studies on voice conversion (VC) are conducted in acoustically matched conditions between source and target signal. However, the robustness of VC methods in presence of mismatch remains unknown. In this paper, we report a comparative analysis of different VC techniques under mismatched conditions. …
New algorithm solves Schrödinger bridge problem with mismatched channels.
SRRM improves recursive transport surrogates in the small-discrepancy regime.
Probabilistic models analyze data by relying on a set of assumptions. Data that exhibit deviations from these assumptions can undermine inference and prediction quality. Robust models offer protection against mismatch between a model's assumptions and reality. We propose a way to systematically detect and mitigate mism…
The family of f-divergences is ubiquitously applied to generative modeling in order to adapt the distribution of the model to that of the data. Well-definedness of f-divergences, however, requires the distributions of the data and model to overlap completely in every time step of training. As a result, as soon as the s…
We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what …
We study the estimation capacity of the generalized Lasso, i.e., least squares minimization combined with a (convex) structural constraint. While Lasso-type estimators were originally designed for noisy linear regression problems, it has recently turned out that they are in fact robust against various types of model un…
Study addresses covariate mismatch in federated learning, improving model accuracy.
A new method improves data generation quality by correcting score mismatches.
This paper presents a method to obtain geometric registrations between high-genus () surfaces. Surface registration between simple surfaces, such as simply-connected open surfaces, has been well studied. However, very few works have been carried out for the registration of high-genus surfaces. The high-genus t…
A new method for inventory control using in-context learning and generative models.
Helical ribbons arise in many biological and engineered systems, often driven by anisotropic surface stress, residual strain, and geometric or elastic mismatch between layers of a laminated composite. A full mathematical analysis is developed to analytically predict the equilibrium deformed helical shape of an initiall…
Our study employs sentiment analysis to evaluate the compatibility of Amazon.com reviews with their corresponding ratings. Sentiment analysis is the task of identifying and classifying the sentiment expressed in a piece of text as being positive or negative. On e-commerce websites such as Amazon.com, consumers can subm…
AIS corrects rollout-training mismatch in quantized RL, improving speed and stability.
New framework for RL transfer learning with state-action mismatch.
KalmanNet uses neural networks to improve state estimation in systems with unknown dynamics.
Co-PLNet combines point and line predictions to improve wireframe parsing accuracy and efficiency.
Subspace models play an important role in a wide range of signal processing tasks, and this paper explores how the pairwise geometry of subspaces influences the probability of misclassification. When the mismatch between the signal and the model is vanishingly small, the probability of misclassification is determined b…
MixMOOD improves SSDL by selecting unlabelled data based on deep feature similarity.
New method improves spatial prediction validation accuracy.
We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demonstrations and an additional RL step that requires environment interactions. However, paired, aligned demonstrations are seldom obtainable an…