New categorical actions link topological and algebraic structures.
problem Understanding relationships between topological and algebraic structures.
method Categorical actions of type B braid group on homotopy categories.
result Proves Rouquier's conjecture on faithfulness of Type B 2-braid group.
ARSM estimator improves gradient backpropagation for categorical variables.
problem Improving gradient backpropagation through categorical variables.
method ARSM combines variable augmentation, REINFORCE, Rao-Blackwellization, and variable swapping.
result ARSM outperforms existing estimators and provides variance reduction methods.
Using a quiver algebra of a cyclic quiver, we construct a faithful categorical action of the extended braid group of affine type A on its bounded homotopy category of finitely generated projective modules. The algebra is trigraded and we identify the trigraded dimensions of the space of morphisms of this category with …
New invariant for links in handlebodies defined using braid groups and Soergel bimodules.
problem Defining invariants for links in handlebodies.
method Using braid groups and complexes of Soergel bimodules.
result Generalized HOMFLYPT homology for links in handlebodies.
Examples of SL(2, Z) actions on differential graded categories are defined and explored.
New algebra connects braid group actions to disc curves.
problem Understanding braid group actions on disc curves.
method Constructed a type B zigzag algebra and showed its categorical action on projective modules.
result Type B braid group action on homotopy category of projective modules.
Adaptive correlated MC improves sequence generation stability.
problem High gradient variance in reinforcement learning for sequence generation.
method Adapts policy gradient estimator using correlated Monte Carlo rollouts.
result Reduces gradient variance and improves model performance.
We show that the action of the mapping class group on bordered Floer homology in the second to extremal spin^c-structure is faithful. This paper is designed partly as an introduction to the subject, and much of it should be readable without a background in Floer homology.
The paper constructs Yang-Baxter solutions using categorical augmented racks.
problem Solutions to the Yang-Baxter equation in knot theory.
method Interpreting augmented racks in tensor categories and constructing solutions using quantum heaps and Hopf algebra modules.
result Explicit constructions and infinite families of Yang-Baxter solutions are provided.
The purpose of this contribution is to point out connections between recent ideas about gerbes and gerbal actions (as higher categorical extension of representation theory) and old discussion in quantum field theory on commutator anomalies, gauge group extensions, and 3-cocycles. The unifying concept is the classical o…
Project uses GANs to recognize facial expressions and emotions from-the-wild with dual model approach.
problem Facial expression and emotion recognition in real-world scenarios.
method Created a dual GAN model architecture for Action Units and Valence Arousal annotations.
result Dual GAN model achieved better results than single model for emotion recognition.
Let X_n be a cycle of n projective lines, and T_n a symplectic torus with n punctures. In this paper we review results appeared in arXiv:1103.2462 and in arXiv:1109.6615, which establish a version of homological mirror symmetry relating X_n and T_n, and define on D^b(Coh(X_n)) an action of the pure mapping class group …
We describe a collection of graded rings which surject onto Webster rings for sl(2) and which should be related to certain categories of singular Soergel bimodules. In the first non-trivial case, we construct a categorical braid group action which categorifies the Burau representation.
New approach categorizes objective functions for embodied agents.
problem Understanding how objectives relate to each other and discovering new objectives.
method Introducing Action Perception Divergence (APD) to categorize objective functions.
result Introduces a spectrum of objectives from narrow to general, explaining various unsupervised objectives.
We discuss the concept of Galois structure and Galois epimorphism in a general setting. Namely, a Galois structure for an epimorphism π:M→B in some category C is the action of a group object that gives to M the structure of principal homogeneous space in the relative category CB.
We give completely combinatorial proofs of the main results of [3] using polygons. Namely, we prove that the mapping class group of a surface with boundary acts faithfully on a finitely-generated linear category. Along the way we prove some foundational results regarding the relevant objects from bordered Heegaard Floe…
This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose cross-label suppression constraint to enlarge the difference among representations for differe…
A new catnat function improves gradient descent for categorical variables.
problem Gradient descent challenges with discrete latent categorical variables.
method Replaced softmax with catnat, a hierarchical binary split function.
result Catnat function offers significant advantages in gradient descent.
When a complex semisimple group G acts holomorphically on a Kähler manifold (X,ω) such that a maximal compact subgroup K⊂G preserves the symplectic form ω, a basic result of symplectic geometry says that the corresponding categorical quotient X/G can be identified with quotient of the zero-set of the m…
In this article we prove that stratified spaces and other geometric subfamilies satisfy categorical Fraïssé properties, a matter that might be of interest for both geometers and logicians. As a motivation we show a new example of a stratified pseudomanifold that satisfies the finite oscillation property with respect to…
The paper constructs a free abelian group from Anosov representations on bundles.
problem Constructing a free abelian group from Anosov representations on bundles.
method Extending the Γ-action via ρ to the space of connections on pullbacks of tangent bundles. result A free abelian group Fab is constructed and acts properly discontinuously on it. The study connects lattices, Garside structures, and weakly modular graphs.
problem Exploring combinatorial non-positive curvature in various simplicial complexes.
method Analyzing lattices with Z-actions and their quotients. result Lattices and their quotients give rise to weakly modular graphs.
StructureBoost improves gradient boosting for complex categorical variables efficiently.
problem Efficiently handling complex categorical variables with known structure.
method Two methods to overcome computational obstacles in SCDT enumeration for structured categorical variables.
result StructureBoost outperforms existing packages on complex categorical problems.
Categorical bundles provide a natural framework for gauge theories involving multiple gauge groups. Unlike the case of traditional bundles there are distinct notions of triviality, and hence also of local triviality, for categorical bundles. We study categorical principal bundles that are product bundles in the categor…
A new method for disentangling action sequences improves model stability.
problem Challenges in unsupervised disentanglement learning due to incomplete theories and abstract notions.
method Introducing disentangling action sequences and a novel fractional variational autoencoder (FVAE) framework.
result FVAE improves the stability of disentanglement for action sequences.
Proposes a taxonomy for economic policies.
problem Lack of a standardized list of economic policies.
method Develops a tree taxonomy to categorize economic policies.
result Constructs an exhaustive list of economic policies.
Bayesian model improves categorization of explosions from sparse data.
problem Challenges in categorizing explosions from limited data.
method Bayesian update to Event Categorization Matrix model with Bayesian Decision Theory.
result Consistent gains in overall accuracy and lower false negative rates.
UNTIE learns representations of coupled categorical data.
problem Challenges in learning from unlabeled categorical data with complex couplings.
method UNTIE approach for unsupervised representation learning of heterogeneous couplings.
result UNTIE significantly improves categorical data representations on 25 diverse datasets.
Paper introduces Categorical Normalizing Flows for better handling of categorical data.
problem Limited application of normalizing flows on categorical data due to lack of intrinsic order.
method Categorical Normalizing Flows use continuous transformations to model latent relations in categorical data, optimizing both continuous representation and model likelihood.
result GraphCNF, a permutation-invariant generative model, outperforms state-of-the-art on molecule generation.
Involutive Hopf monoids yield surface invariants.
problem Involutive Hopf monoids in symmetric monoidal categories.
method Construction of invariants via (co)equalizers and images.
result Categorical generalization of quantum double models.
This paper proposes a method to reduce complexity in GLMs with categorical predictors.
problem Wasteful, hard-to-interpret, and prone to overfitting of traditional one-hot encoding for high-cardinality categorical predictors.
method Clustering categories of categorical predictors through a numerical method that preserves or improves accuracy while reducing the number of coefficients.
result Clustering categories of categorical predictors reduces complexity substantially without harming accuracy.
A new method optimises problems with both continuous and categorical inputs.
problem Optimising black-box problems with mixed continuous and categorical inputs.
method Continuous and Categorical Bayesian Optimisation (CoCaBO) combining multi-armed bandits and Bayesian optimisation.
result CoCaBO outperforms existing methods on synthetic and real-world tasks.
The paper shows how integrating categorical semantics can enhance unsupervised domain translation.
problem Improving unsupervised domain translation between perceptually different domains.
method Learning invariant categorical semantic features in an unsupervised manner and conditioning them on the style encoder.
result Conditioning the style encoder on learned categorical semantics improves translation and stylization.
Smooth actions of infinite groups linked to homotopy theory.
problem Connecting infinite-dimensional smooth groups to homotopy theory.
method Two computations: diffeological homotopy groups and localization of a strict category.
result Natural constructions yield homotopically coherent group actions of G.
Categorical variables are a natural choice for representing discrete structure in the world. However, stochastic neural networks rarely use categorical latent variables due to the inability to backpropagate through samples. In this work, we present an efficient gradient estimator that replaces the non-differentiable sa…
New algorithm recovers labels from noisy categorical data.
problem Recovering latent labels from noisy observations in structured instances.
method Approximate algorithm for graphs with categorical variables.
result Logarithmic dependency of Hamming error to the number of categories.
Study categorizes mutual funds using natural language processing from unstructured data.
problem Categorizing mutual funds using unstructured data for financial analysis.
method Used natural language processing models to classify mutual funds from their investment strategy descriptions.
result High accuracy in categorizing mutual funds using NLP from unstructured data.
Paper improves anomaly detection and categorization in multi-cloud environments.
problem Differentiating among different types of attacks for better defense.
method Used supervised machine learning techniques (LR and RF) on a public dataset.
result More than 99% detection accuracy and 93.6% categorization accuracy.
Develops 2-categorical methods for multi-parameter persistence.
problem Fundamental limitations of traditional persistence modules.
method 2-categorical structures to capture hierarchical interactions.
result New invariants effectively characterize multidimensional topological features.
Transforms classical connections using pushforwards and gauge transformations.
problem Transforming classical connections in categorical settings.
method Constructing pushforwards and applying gauge transformations to decorated path spaces.
result Combines traditional gauge transformation with affine translation.
The paper explores efficient ways to represent categorical data.
problem Wasteful one-hot encoding of categorical variables.
method Investigates alternative, lower-dimensional real-valued representations.
result Proposed methods retain all predictive information without one-hot encoding.
CADM proposes a cluster-specific distance metric for categorical data clustering.
problem Inadequate distance metrics for categorical data, especially varying within clusters.
method Cluster-customized adaptive distance metric for categorical data.
result Achieved competitive performance in categorical data clustering.
Develops a new method for decision trees using categorical variable structure.
problem Lack of structure in treating categorical variables as predictors.
method Introduces a mathematical framework to represent categorical structure and generalizes decision trees to utilize this structure.
result Improves prediction accuracy on weather data using the new method.
Categorical d-separation criterion simplifies probability graph analysis.
problem Detecting causal relationships in probability distributions.
method Introducing categorical definitions for causal models and d-separation.
result Abstract version of d-separation criterion applies to various probability theories.
Paper proposes a novel trading strategy combining clustering and reinforcement learning for multi-period portfolio management.
problem Developing an effective trading strategy for multi-period portfolio management.
method The paper integrates clustering techniques with reinforcement learning to categorize and manage stocks across multiple trading periods.
result The proposed strategy outperforms conventional techniques in various metrics, achieving an average return of 151% over 360 trading periods.
nTreeClus clusters categorical sequences using tree-based learners and k-mers.
problem Challenges in clustering categorical and sequential data.
method nTreeClus uses Tree-based Learners, k-mers, and autoregressive models for categorical time series.
result nTreeClus outperformed baseline methods in various validation metrics.
Study extends cognitive modeling to natural images, revealing the importance of image representation.
problem Extending cognitive modeling to natural images and understanding human categorization.
method Conducted a large-scale study with over 500,000 human judgments. Used deep and shallow machine learning methods to represent images. Applied psychological models of categorization to natural images.
result Simple models with abstract prototypes outperform complex exemplar accounts when using expressive, data-driven image representations.
A new gradient estimator for categorical distributions reduces bias and variance.
problem Intractability of gradients for categorical distributions in discrete latent variable models.
method CatLog-Derivative trick and IndeCateR gradient estimator.
result IndeCateR reduces bias and variance of gradients for categorical distributions.