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.
Efficient algorithms learn from coarse labels instead of fine grained ones.
Fine-grained pretraining improves neural network's ability to learn rare features.
Paper presents UrbanFM and UrbanPy models for inferring fine-grained urban flows.
We propose a probabilistic model for refining coarse-grained spatial data by utilizing auxiliary spatial data sets. Existing methods require that the spatial granularities of the auxiliary data sets are the same as the desired granularity of target data. The proposed model can effectively make use of auxiliary data set…
Paper tackles cross-granularity few-shot learning with meta-embedder.
New framework learns labels at both bag and graph levels.
We introduce a hierarchical architecture for video understanding that exploits the structure of real world actions by capturing targets at different levels of granularity. We design the model such that it first learns simpler coarse-grained tasks, and then moves on to learn more fine-grained targets. The model is train…
Tensor network architecture for classification and regression using wavelet transformations.
Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accelerators such as TPU. The structure of sparsity, i.e., the granularity of pruning, affects the efficiency of hardware accelerator design as w…
Improved investment performance with fine-grained LLM tasks.
Proposes a method to predict stock movements using fine-grained events from finance news.
New method uses LLMs to generate detailed scientific hypotheses.
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT). However, due to the especially expensive and labor-intensive labeling, existing public corpora in AT-level are…
LDA improves image classification accuracy with fewer features.
Fine-grained gap-dependent regret bounds for reinforcement learning.
ECN framework improves training on noisy structured labels.
The paper develops a framework for abstracting causal models using category theory.
We discuss a Bayesian formulation to coarse-graining (CG) of PDEs where the coefficients (e.g. material parameters) exhibit random, fine scale variability. The direct solution to such problems requires grids that are small enough to resolve this fine scale variability which unavoidably requires the repeated solution of…
The combination of high-dimensionality and disparity of time scales encountered in many problems in computational physics has motivated the development of coarse-grained (CG) models. In this paper, we advocate the paradigm of data-driven discovery for extract- ing governing equations by employing fine-scale simulation …
LEAK learns from mistakes to improve point cloud segmentation.
Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method. There are currently two mainstreams of pruning methods representing two extremes of pruning reg…
Consider a classification problem where we do not have access to labels for individual training examples, but only have average labels over subpopulations. We give practical examples of this setup and show how such a classification task can usefully be analyzed as a weakly supervised clustering problem. We propose thre…
Improved object detection for scientific document images.
Fine-grained event tagging system for SEC 8-K filings improves precision to 96%.
TOCO framework compresses neural networks based on tolerance analysis.
Novel method diagnoses large language models' reasoning abilities.
Generative framework learns effective, lower-dimensional models from high-dimensional data.
Identifies most probable flows for Kunita SDEs in fluid dynamics.
The precise diagnosis is of great significance in developing precise treatment plans to restore neck function and reduce the burden posed by the cervical spondylosis (CS). However, the current available neck function assessment method are subjective and coarse-grained. In this paper, based on the relationship among CS,…
Paper develops fine-grain spatiotemporal risk scores using high-resolution mobility data.
Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may result in a significant improvement in both convergence and generalization performanc…
Residual Prior Diffusion integrates coarse latent priors with diffusion models for better generative tasks.
We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during training, the network tends to learn coarse-grained features, whereas when the input is …
Sig-DEG speeds up diffusion models by distilling them into faster approximations.
Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems. Deep autoregressive models suffer from error propagation which becomes catastrophic for imputing long-range sequences. In this paper, we take a non-autoregressive approach and propose …
Census data provide detailed information about population characteristics at a coarse resolution. Nevertheless, fine-grained, high-resolution mappings of population counts are increasingly needed to characterize population dynamics and to assess the consequences of climate shocks, natural disasters, investments in infr…
Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones. In contrast to both extremes, real world recognition problems exhibit heavy-tailed class distributions, with cluttered scenes and a mix of coarse and fi…
Unified framework for hierarchical image classification with epistemic uncertainty.
PSimGNN partitions graphs into subgraphs for efficient graph similarity computation.
Paper reduces neural network complexity for image classification.
Decision-tree-based ensemble classification methods (DTEMs) are a prevalent tool for supervised anomaly detection. However, due to the continued growth of datasets, DTEMs result in increasing drawbacks such as growing memory footprints, longer training times, and slower classification latencies at lower throughput. In …
DataRater learns which data points are most valuable for training models.
Study semi-coarse spaces' homotopy and homology, extending coarse geometry.
We address the problem of \emph{instance label stability} in multiple instance learning (MIL) classifiers. These classifiers are trained only on globally annotated images (bags), but often can provide fine-grained annotations for image pixels or patches (instances). This is interesting for computer aided diagnosis (CAD…
We define a notion of free product for coarse spaces that generalizes the corresponding notion of a free product for groups. We show that free products preserve coarse properties such as coarse property C, finite coarse decomposition complexity, and coarse property A. We also give an upper bound estimate on the dimensi…
Defines coarse cohomology of space complements, proving new duality results.
For every strong coarse homology theory we construct a coarse assembly map as a natural transformation between coarse homology theories. We provide various conditions implying that this assembly map is an equivalence. These results generalize known results for the analytic coarse assembly map for K-homology to general …
This paper evaluates targeted data poisoning attacks by focusing on the hardest samples, improving evaluation and defense strategies.