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.
Paper explores how to use mixed types of side information for better recommendations.
The study examines flat S1-bundles and their homology groups, focusing on analytic vs smooth conditions.
The step of expert taxa recognition currently slows down the response time of many bioassessments. Shifting to quicker and cheaper state-of-the-art machine learning approaches is still met with expert scepticism towards the ability and logic of machines. In our study, we investigate both the differences in accuracy and…
Typically, Softmax is used in the final layer of a neural network to get a probability distribution for output classes. But the main problem with Softmax is that it is computationally expensive for large scale data sets with large number of possible outputs. To approximate class probability efficiently on such large sc…
HKT improves sequence processing with multi-scale attention and kernel analysis.
The study proves non-existence of Cannon-Thurston maps for certain groups.
Paper investigates methods to improve classification by inducing a hierarchy from flat labels.
In this paper, we exhibit the tradeoffs between the (training) sample, computation and storage complexity for the problem of supervised classification using signal subspace estimation. Our main tool is the use of tensor subspaces, i.e. subspaces with a Kronecker structure, for embedding the data into lower dimensions. …
The cooperative hierarchical structure is a common and significant data structure observed in, or adopted by, many research areas, such as: text mining (author-paper-word) and multi-label classification (label-instance-feature). Renowned Bayesian approaches for cooperative hierarchical structure modeling are mostly bas…
Paper introduces hierarchical softmax for global hierarchical classification tasks.
The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years. In spite of the advance, clustering with representation learning has been limited to flat-level categories, which often involves cohesive clustering with a focus on instance relations.…
There has been a surge in the number of large and flat data sets - data sets containing a large number of features and a relatively small number of observations - due to the growing ability to collect and store information in medical research and other fields. Hierarchical clustering is a widely used clustering tool. I…
Hierarchical CNNs improve diagnosis of GI diseases from histopathological images.
Study compares local and global models for hierarchical forecasting accuracy.
New framework detects near vs. far out-of-distribution samples for AI safety.
Transformer models perform slower than convolutional networks in learning hierarchical language structures.
HCC extends conformal prediction to handle class hierarchies, improving prediction reliability.
In our work, we propose to represent HTM as a set of flat models, or layers, and a set of topical hierarchies, or edges. We suggest several quality measures for edges of hierarchical models, resembling those proposed for flat models. We conduct an assessment experimentation and show strong correlation between the propo…
We propose a new splitting criterion for a meta-learning approach to multiclass classifier design that adaptively merges the classes into a tree-structured hierarchy of increasingly difficult binary classification problems. The classification tree is constructed from empirical estimates of the Henze-Penrose bounds on t…
Deep learning models based on CNNs are predominantly used in image classification tasks. Such approaches, assuming independence of object categories, normally use a CNN as a feature learner and apply a flat classifier on top of it. Object classes in many settings have hierarchical relations, and classifiers exploiting …
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which …
Efficient algorithm for evaluating hierarchical classification methods at multiple operating points.
FOSC-X: An extended framework for extracting multiple optimal flat clusterings from hierarchical cluster trees
New group not biautomatic, geometrically constructed.
Bagging and boosting are proved to be the best methods of building multiple classifiers in classification combination problems. In the area of "flat clustering" problems, it is also recognized that multi-clustering methods based on boosting provide clusterings of an improved quality. In this paper, we introduce a novel…
We present Multitask Soft Option Learning(MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational posteriors for each task, regularized by a shared prior. This ''soft'' version of options avoids several instabilities during training in a …
Paper studies multiclass classifiers from binary classifiers, proving methods and demonstrating advantages.
Dropout is a very effective method in preventing overfitting and has become the go-to regularizer for multi-layer neural networks in recent years. Hierarchical mixture of experts is a hierarchically gated model that defines a soft decision tree where leaves correspond to experts and decision nodes correspond to gating …
t-NEB clusters high-dimensional data hierarchically with density paths.
New model shows hierarchical proof structure helps theorem provers.
Nonparametric models are versatile, albeit computationally expensive, tool for modeling mixture models. In this paper, we introduce spectral methods for the two most popular nonparametric models: the Indian Buffet Process (IBP) and the Hierarchical Dirichlet Process (HDP). We show that using spectral methods for the in…
Proposes a hierarchical curriculum loss to improve model accuracy and interpretability.
HC-GNN tackles long-range graph information and high-order neighbourhoods.
FISHDBC clusters arbitrary data with flexible, scalable, and hierarchical features.
Contrastive learning properties studied, including feature suppression and hierarchical learning.
Hybrid Bayesian-conformal framework improves uncertainty quantification in healthcare predictions.
An analysis of the Japanese credit market in 2004 between banks and quoted firms is done in this paper using the tools of the networks theory. It can be pointed out that: (i) a backbone of the credit channel emerges, where some links play a crucial role; (ii) big banks privilege long-term contracts; the "minimal spanni…
Improved VAEs learn flat latent spaces for better data similarity.
CoHiRF extends clustering methods to handle high-dimensional data efficiently.
We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep…
HRL4IN tackles interactive navigation tasks with mobile manipulators, improving efficiency and performance.
New model infers causal relationships from spatio-temporal data, even with unobserved confounders.
Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures. We unite the two via adaptive neur…
VR game data for P300 BCI with raccoon vs demon stimuli.
Paper improves SOMs for non-Euclidean data modeling.
We introduce a new multi-dimensional nonlinear embedding -- Piecewise Flat Embedding (PFE) -- for image segmentation. Based on the theory of sparse signal recovery, piecewise flat embedding with diverse channels attempts to recover a piecewise constant image representation with sparse region boundaries and sparse clust…
Here, we present the World Trade Atlas 1870-2013, a collection of annual world trade maps in which distance combines economic size and the different dimensions that affect international trade beyond mere geography. Trade distances, which are based on a gravity model predicting the existence of significant trade channel…
A new reinforcement learning approach using competitive primitives that specialize and specialize based on information needs.