Paper presents IPRC for robust tumor recognition using sparse representation.
problem Sparse representation methods struggle with insufficient test samples and instability.
method Proposes IPRC, a stable inverse projection representation method.
result Demonstrates competitive robust tumor recognition using IPRC.
The present paper is a contribution to categorial index theory. Its main result is the calculation of the Pfaffian line bundle of a certain family of real Dirac operators as an object in the category of line bundles. Furthermore, it is shown how string structures give rise to trivialisations of that Pfaffian.
Attribute-aware CF models aims at rating prediction given not only the historical rating from users to items, but also the information associated with users (e.g. age), items (e.g. price), or even ratings (e.g. rating time). This paper surveys works in the past decade developing attribute-aware CF systems, and discover…
Gauge theory connects principal bundles and functors.
problem Understanding the relationship between principal bundles and functors.
method Characterized association functors and established an equivalence between principal bundles and functors.
result Established an equivalence between principal bundles and functors using association functors.
DisCoPyro combines category theory with machine learning for program learning.
problem Applying category theory to machine learning tasks.
method Introducing DisCoPyro, a framework combining categorical structures with amortized variational inference.
result DisCoPyro can be applied in program learning for variational autoencoders and potentially contributes to AGI.
Open category detection is the problem of detecting "alien" test instances that belong to categories or classes that were not present in the training data. In many applications, reliably detecting such aliens is central to ensuring the safety and accuracy of test set predictions. Unfortunately, there are no algorithms …
MILCCI integrates labels across categories for better understanding of multi-trial data.
problem Understanding how labels encode multi-trial observations and disentangling their effects.
method Sparse per-trial decomposition leveraging label similarities within each category.
result MILCCI identifies interpretable components and integrates label information.
One of the main open problems in the theory of multi-category margin classification is the form of the optimal dependency of a guaranteed risk on the number C of categories, the sample size m and the margin parameter gamma. From a practical point of view, the theoretical analysis of generalization performance contribut…
New Frank-Wolfe algorithm speeds up SVM-type multi-category learning.
problem Improving pattern recognition performance in multi-category SVM learning.
method Developed a new optimization algorithm based on Frank-Wolfe framework for MC-SVM variants.
result Closed-form solutions for direction finding and line search in the Frank-Wolfe framework for MC-SVM.
Review of deep learning methods in medical image registration.
problem Improving accuracy and efficiency of medical image registration.
method Classification and detailed analysis of seven categories of DL-based registration methods.
result Comprehensive comparison of DL-based methods for lung and brain registration.
Diffusion in a linear potential in the presence of position-dependent killing is used to mimic a default process. Different assumptions regarding transport coefficients, initial conditions, and elasticity of the killing measure lead to diverse models of bankruptcy. One "stylized fact" is fundamental for our considerati…
Overview of 3D TQFTs and 3-manifold invariants.
problem Quantum invariants of 3-manifolds.
method Recall and review of TQFTs, fusion categories, and recent generalizations.
result Overview of various 3D TQFTs and their invariants.
Two-stage neural network for few-shot image recognition.
problem Few-shot image recognition for novel categories.
method Multi-layer neural network with feature extraction and classification stages.
result Competitive performance on four standard datasets.
Following widely used in visual recognition concept of relative attributes, the article establishes definition of the relative PCA attributes for a class of objects defined by vectors of their parameters. A new rating model (RELARM) is built using relative PCA attribute ranking functions for rating object description a…
Study categorizes and analyzes emotions in sexist tweets.
problem Lack of defined categories for sexism in NLP.
method Used a new dataset from SemEval-2018 to classify and analyze emotions in sexist tweets.
result Demonstrated the mental state and affectual state of users who tweet in different categories of sexism.
Proposes categorification of Z-invariants for specific 3-manifolds.
problem Categorification of Z-invariants for negative definite plumbed 3-manifolds.
method Abelian categorification using 3d N=2 theory and log VOAs.
result Nested Weyl-type character formulas reconstruct Z^-invariants. Model predicts drug overdose hotspots using EMS and toxicology data.
problem Predicting drug overdose hotspots to focus limited services.
method Spatial-temporal point process model integrating EMS and toxicology data.
result Model improves prediction accuracy by integrating heterogeneous data.
In this work, we propose an end-to-end block-based auto-encoder system for image compression. We introduce novel contributions to neural-network based image compression, mainly in achieving binarization simulation, variable bit rates with multiple networks, entropy-friendly representations, inference-stage code optimiz…
Investigates chaotic financial time series with monthly contributions and devaluation.
problem Analyzing chaotic behavior in financial processes with piecewise contributions and negative interest rates.
method Examines a financial process with monthly contributions and devaluation, showing dichotomy in behavior.
result Financial time series exhibit either periodic sequences or Cantor set of ω-limit points, with chaotic behavior at points of a Cantor attractor.
Unified framework connects deformation theory and derived categories for multiparameter persistence.
problem Algebraic complexity of multiparameter persistence modules hinders classification, stability, and interpretability.
method Combines deformation theory and derived categories to study multiparameter persistence geometrically.
result Unified conjecture relating interleaving distance to derived convolution metrics established.
New model corrects bias in crowdsourced ratings for diverse items.
problem Bias and noise in crowdsourced ratings for training data.
method Bayesian rating model with item-level effects for difficulty, discriminativeness, and guessability.
result New model avoids bias in training data, improving model goodness of fit.
Theory extends optimal learning rates without realizability assumption.
problem Agnostic binary classification without realizability assumption.
method Identifies tetrachotomy of optimal rates and combinatorial structures.
result Optimal universal rates for binary classification in agnostic setting.
Defines a new short rate model and convexity adjustment formulae.
problem Interest rate convexity in a Gaussian framework.
method Defines a short rate model driven by a Gaussian Volterra process and derives convexity adjustment formulae.
result Explicit formulae for convexity adjustment derived.
The main contribution of this article is a new prior distribution over directed acyclic graphs, which gives larger weight to sparse graphs. This distribution is intended for structured Bayesian networks, where the structure is given by an ordered block model. That is, the nodes of the graph are objects which fall into …
Understanding urban growth is one with understanding how society evolves to satisfy the needs of its individuals in sharing a common space and adapting to the territory. We propose here a quantitative analysis of the historical development of a large urban area by investigating the spatial distribution and the age of c…
The consultative papers for the Basel II Accord require rating systems to provide a ranking of obligors in the sense that the rating categories indicate the creditworthiness in terms of default probabilities. As a consequence, the default probabilities ought to present a monotonous function of the ordered rating catego…
The Wallenius distribution is a generalisation of the Hypergeometric distribution where weights are assigned to balls of different colours. This naturally defines a model for ranking categories which can be used for classification purposes. Since, in general, the resulting likelihood is not analytically available, we a…
PC-GAIN improves GAIN's imputation by incorporating category information.
problem Missing data in incomplete datasets.
method Pre-training with pseudo-labels and incorporating an auxiliary classifier into GAIN.
result Significantly improved imputation quality compared to GAIN.
JD.com uses a new CNN model to improve ad click prediction.
problem Improving CTR prediction for ads with visual content.
method Proposes Category-specific CNN (CSCNN) to incorporate category knowledge early in the feature extraction process.
result CSCNN outperforms existing methods in CTR prediction.
Proposes a Manifold Graph for semi-supervised image classification.
problem Improving semi-supervised image classification with limited labeled data.
method Graph networks for feature extraction, graph connectivity, and feature propagation. Prototype Generator for unlabeled data representation.
result Achieves state-of-the-art performance with significantly fewer labeled data.
Study shows survivorship bias inflates returns in India's small-cap index.
problem Survivorship bias in emerging market small-cap indices.
method Reconstructing historical index composition through market capitalization ranking and comparing equal-weight portfolios of current constituents versus all historical members.
result Survivor-only backtesting overstates returns by 4.94 percentage points and Sharpe ratios by 0.097.
Enhances machine learning interpretability using category theory.
problem Improving machine learning interpretability and social implementation.
method Develops a categorical framework for structured understanding of supervised learning.
result Introduces the Gauss-Markov Adjunction for clarifying residuals and parameters.
Develops a category-theoretic approach to interpret conformal prediction.
problem Interpreting conformal prediction as a quantitative uncertainty tool.
method Category-theoretic approach to represent and decompose conformal prediction.
result Decomposes conformal prediction into two steps: predictive distributions and prediction regions.
Study examines cyber losses across sectors, finds high severity and frequency.
problem Understanding the nature of cyber losses and their variability across sectors.
method Analysis of a leading industry dataset of cyber events, focusing on frequency and severity.
result Cyber risks are heavy-tailed, with high probability of extreme losses.
This study examines whether tokenized assets improve liquidity and finds significant differences across categories.
problem Improving liquidity for real-world assets through tokenization.
method Examined tokenized real-world assets using Ethereum-based data, measuring liquidity through turnover, active addresses, and active-month indicator.
result Gold-backed tokens show more persistent on-chain activity than Treasury and private-credit-related products, but asset value alone does not reliably predict liquidity.
EPEM efficiently estimates parameters for monotone missing data.
problem Efficiently estimating parameters for monotone missing data.
method Derive exact formulas and propose EPEM algorithm for multiple class, monotone missing datasets.
result EPEM reduces error rates significantly and is faster than other methods.
Machine learning analyzed peer reviews to find differences in quality by journal impact factor.
problem Determining if higher journal impact factors correlate with more thorough or helpful peer reviews.
method Hand-coded and machine-learned analysis of 10,000 peer review sentences from 1,644 journals.
result Peer reviews in higher impact factor journals are more thorough in discussing methods but less helpful in suggesting solutions and providing examples.
Recommending items to users is a challenging task due to the large amount of missing information. In many cases, the data solely consist of ratings or tags voluntarily contributed by each user on a very limited subset of the available items, so that most of the data of potential interest is actually missing. Current ap…
Study quantifies systemic risk in DeFi using network analysis.
problem Systemic risk in decentralized finance (DeFi) ecosystem.
method Network-based fragility analysis of TVL dynamics.
result Developed CFI and RCS to quantify structural fragility and risk contribution.
Underrepresented scientists produce more novel work but it's undervalued.
problem Underrepresented groups in science face undervaluation of their innovations.
method Text analysis and machine learning of career data of over 1 million US doctoral recipients.
result Underrepresented groups produce more scientific novelty but their contributions are undervalued.
Proposes a mixed pension system combining PAYG and funded contributions to address sustainability.
problem Sustainability of public pension systems due to declining birth rates and increasing life expectancy.
method Combines a classical PAYG scheme with a funded investment scheme to ensure financial sustainability.
result Individuals contribute to a funded part, making them active participants in addressing demographic risks.
Modern online platforms rely on effective rating systems to learn about items. We consider the optimal design of rating systems that collect binary feedback after transactions. We make three contributions. First, we formalize the performance of a rating system as the speed with which it recovers the true underlying ran…
We explore a new way to evaluate generative models using insights from evaluation of competitive games between human players. We show experimentally that tournaments between generators and discriminators provide an effective way to evaluate generative models. We introduce two methods for summarizing tournament outcomes…
Improved SGD methods converge faster for nonconvex optimization.
problem Nonconvex optimization challenges in machine learning.
method Adaptive SGD with line-search and Polyak stepsizes.
result Unified convergence rates for various nonconvex functions.
Smooth FFT from B-fields and D-branes.
problem Constructing a smooth functorial field theory from B-fields and D-branes.
method Definition of a smooth bordism category, transgression, functoriality, thin homotopy invariance, positive reflection structure.
result Generalizes open-closed TQFTs to include target spaces and open strings.
Studies amenable category's monotonicity and its relation to topological complexity.
problem Monotonicity of amenable category for degree-one maps.
method Uses amenable covers and compares with topological complexity.
result Establishes a relation between amenable category and topological complexity.
To each oriented surface S, we associate a differential graded category Ko(S). The homotopy category Ho(Ko(S)) is a triangulated category which satisfies properties akin to those of the contact categories studied by K. Honda. These categories are also related to the algebraic contact categories of Y. Tian and to the bo…
FedCM measures contributions in real-time for federated learning.
problem Fairly allocating contributions in federated learning systems.
method FedCM calculates impact based on current and previous rounds with attention aggregation.
result FedCM is more sensitive to data quality and quantity in real-time.