Study expands multiclass classification models with new rates and partial concept classes.
problem Multiclass classification with a bounded number of labels under various conditions.
method Extends traditional PAC model to distribution-dependent and data-dependent learning rates, characterizes optimal rates for universal and partial concept classes.
result Characterizes three types of learning rates (exponential, linear, arbitrarily slow) for fixed distributions and complexity measures for partial concept classes.
Extends PAC learning theory to handle partial concepts with special properties.
problem Traditional PAC learning theory cannot handle tasks with special data properties.
method Introduces partial concepts and new PAC learning framework.
result Partial concept classes cannot be captured by traditional PAC theory.
New concept of partial law invariance connects decision theory and financial risk management.
problem Connecting decision theory and financial risk management under uncertainty.
method Characterizing partially law-invariant coherent risk measures via a novel representation formula.
result Strong partial law invariance bridges the gap between existing risk measure representations.
New concept of partial comonotonicity connects riskmetrics and dependence.
problem Understanding and quantifying risk metrics under partial comonotonicity.
method Developed a new notion of partial comonotonicity and established its connection to distortion riskmetrics.
result Partial comonotonicity uniquely characterizes a class of distortion riskmetrics through additivity.
The study explores polarized deformations of SKT Calabi-Yau manifolds using Aeppli classes.
problem Understanding polarized deformations of SKT Calabi-Yau manifolds.
method Introducing small deformations polarized by Aeppli classes and investigating their properties.
result Existence of primitive elements in Bott-Chern classes and metrics comparison.
PCBM improves neural network generalization by partially observing concepts.
problem Decreased generalization performance due to observing all concepts in CBM.
method Developed a theoretical analysis of PCBM's Bayesian generalization error.
result PCBM's generalization error is lower than CBM's due to partial concept observation.
Generalizes Anosov flows to partially hyperbolic diffeomorphisms.
problem Classifying partially hyperbolic diffeomorphisms.
method Introducing collapsed Anosov flows and self orbit equivalences.
result All examples in Bonatti et al. belong to the collapsed Anosov flow class.
Given a compact complex n-fold X satisfying the ∂∂ˉ-lemma and supposed to have a trivial canonical bundle KX and to admit a balanced (=semi-Kähler) Hermitian metric ω, we introduce the concept of deformations of X that are {\bf co-polarised} by the balanced class $[ω^{n-1}]\in H^{n-1,\,n-1…
We use partial class memberships in soft classification to model uncertain labelling and mixtures of classes. Partial class memberships are not restricted to predictions, but may also occur in reference labels (ground truth, gold standard diagnosis) for training and validation data. Classifier performance is usually ex…
This work proves DP learnability implies online learnability for general classification tasks.
problem Link between differential privacy and online learning for general classification tasks.
method Establishes Ramsey-type theorems for trees to prove DP learnability implies online learnability.
result DP learnability implies online learnability for general classification tasks.
New algorithm learns efficiently with a simple 'yes/no' oracle.
problem Can efficient learning be achieved with a simpler oracle than ERM?
method Developed an oracle that returns 'yes' or 'no' for realizable datasets.
result Learnability is possible with a polynomial price in VC dimension.
CPPO learns policies from partial offline data in MDPs with structural assumptions.
problem Offline Reinforcement Learning with partial coverage assumption.
method Constrained Pessimistic Policy Optimization (CPPO) using a function class and model class constraint.
result CPPO achieves PAC guarantee with partial coverage, learning competitive policies.
We extend the concept of renormalized volume for geometrically finite hyperbolic 3-manifolds, and show that is continuous for geometrically convergent sequences of hyperbolic structures over an acylindrical 3-manifold M with geometrically finite limit. This allows us to show that the renormalized volume attains its…
We write the Dirac equation in curved 4-dimensional Lorentzian spacetime using concepts from the analysis of partial differential equations as opposed to geometric concepts.
In this paper, we introduce the concept of the independence graph of a directed 2-complex. We show that the class of diagram groups is closed under graph products over independence graphs of rooted 2-trees. This allows us to show that a diagram group containing all countable diagram groups is a semi-direct product of a…
The paper reviews and extends calibration concepts for classification and regression.
problem Formalizing compatibility between probabilistic predictions and outcomes.
method Review and extension of existing calibration concepts, introduction of new concepts.
result Hierarchical relations between calibration concepts for various data types.
Research on mixed polynomials, extending non-degeneracy concepts to complex variables.
problem Extending non-degeneracy concepts to mixed polynomials in complex variables.
method Generalization of Mondal's partial non-degeneracy to mixed polynomials, introducing new concepts and proving properties.
result Strong partial non-degeneracy implies isolated singularities, and mixed polynomials that are strongly inner non-degenerate satisfy the strong Milnor condition.
For a smooth (locally trivial) principal bundle in Ehresmann's sense, the relation between the commuting vertical and horizontal actions of the structural Lie group and the structural Lie groupoid (isomorphisms between vertical fibers) is regarded as a special case of a symmetrical concept of conjugation between "princ…
Machine learning offers novel ways and means to design personalized learning systems wherein each student's educational experience is customized in real time depending on their background, learning goals, and performance to date. SPARse Factor Analysis (SPARFA) is a novel framework for machine learning-based learning a…
We solve a broad class of sequential decision-making problems with partially observed states.
problem Sequential decision-making under uncertainty with partially observed states.
method Modeling as a partially observed Markov decision process (POMDP) and separating state and modulation process.
result The approach allows for specialized approximate solution procedures.
In this review paper we discuss the different interpretations of the concept of connection in a fiber bundle and in a jet bundle, and relate it with first and second-order systems of partial differential equations (PDE's) and multivector fields. As particular cases we analyze the concepts of linear connections and conn…
The paper defines a new Lie groupoid concept for infinite dimensions.
problem Obstacles in infinite-dimensional Lie groupoids.
method Introduces a new notion of 'bi-algebroid' for infinite dimensions.
result Recover partial Poisson manifolds and Banach Poisson Lie groups.
In this paper we extend the concept of Competitivity Graph to compare series of rankings with ties ({\em partial rankings}). We extend the usual method used to compute Kendall's coefficient for two partial rankings to the concept of evolutive Kendall's coefficient for a series of partial rankings. The theoretical frame…
Characterizes concept classes for optimistic online learning.
problem Understanding minimal assumptions for online learnability.
method Investigates two questions about concept classes' learnability.
result Characterizes all concept classes for optimistically universal online learnability.
ECBMs unify concept-based interpretations in deep learning models.
problem Suboptimal final accuracy and lack of concept interaction and conditional dependencies.
method ECBMs use a set of neural networks to define joint energy, enabling concept correction and conditional dependency quantification.
result ECBMs achieve higher accuracy and richer concept interpretations compared to state-of-the-art methods.
Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches have been developed in literature to deal with the problem of drift handling an…
Strict partial order is a mathematical structure commonly seen in relational data. One obstacle to extracting such type of relations at scale is the lack of large-scale labels for building effective data-driven solutions. We develop an active learning framework for mining such relations subject to a strict order. Our a…
PDD detects concept drift using explainable AI, improving model performance in dynamic environments.
problem Detecting and adapting to concept drift in predictive models.
method Profile Drift Detection (PDD) using Partial Dependence Profiles (PDPs).
result PDD outperforms existing methods in detecting concept drift and maintaining high predictive performance.
CREAM models enable concept-grounded predictions and interpretability.
problem Designing models that can encode and extend prior knowledge about concept-concept and concept-task relationships.
method Proposes a flexible and efficient framework (CREAMs) that encodes arbitrary C−C and CoY relationships, incorporating a side-channel for incomplete concept sets. result CREAM models achieve competitive task performance while encouraging concept-grounded predictions, avoiding concept leakage and achieving black-box-level performance.
We introduce the concept of partial Poisson structure on a manifold M modelled on a convenient space. This is done by specifying a (weak) subbundle T′M of T∗M and an antisymmetric morphism P:T′M→TM such that the bracket {f,g}P=−<df,P(dg)> defines a Poisson bracket on the …
The study identifies latent concepts from diverse observations without assuming specific models.
problem Lack of general theoretical support for concept learning.
method Develops a nonparametric framework for identifying latent concepts from multiple classes of observations.
result Correctness guarantees for concept identification without parametric assumptions.
Embedding methods which enforce a partial order or lattice structure over the concept space, such as Order Embeddings (OE) (Vendrov et al., 2016), are a natural way to model transitive relational data (e.g. entailment graphs). However, OE learns a deterministic knowledge base, limiting expressiveness of queries and the…
The notions of stable and Morse subgroups of finitely generated groups generalize the concept of a quasiconvex subgroup of a word-hyperbolic group. For a word-hyperbolic group G, Kapovich provided a partial algorithm which, on input a finite set S of G, halts if S generates a quasiconvex subgroup of G and run…
This research generates synthetic data streams for handling concept drifts and novel classes.
problem Handling concept drifts and novel classes in dynamic data streams.
method Synthetic data stream generation for both concept drifts and novel classes.
result Demonstrates the effectiveness of unsupervised drift detectors in open set recognition.
Paper translates train track concepts to cluster algebras for pseudo-Anosov mapping classes.
problem Understanding pseudo-Anosov mapping classes on surfaces.
method Using Goncharov--Shen's potential function, the paper translates train track concepts into cluster algebra language.
result Proves sign stability of general pseudo-Anosov mapping classes.
How many bits of information are revealed by a learning algorithm for a concept class of VC-dimension d? Previous works have shown that even for d=1 the amount of information may be unbounded (tend to ∞ with the universe size). Can it be that all concepts in the class require leaking a large amount of inform…
We investigate the problem of describing the homotopy classes [X,Y] of continuous functions between ω-bounded non metrizable manifolds X,Y. We define a family of surfaces X built with the first octant C in L2 (L is the longline and R the longray), and show that [X,R] is in bijection with so called `a…
On a compact ∂∂ˉ-manifold X, one has the Hodge decomposition: the de Rham cohomology groups split into subspaces of pure-type classes as HdRk(X)=⊕p+q=kHp,q(X), where the Hp,q(X) are canonically isomorphic to the Dolbeault cohomology groups H∂ˉp,q(X). F…
Paper analyzes iterative learning for concept classes and learns half-spaces.
problem Learning concept classes efficiently with iterative learners.
method Analyzes various settings of iterative learning and provides a constructive algorithm for half-spaces.
result Constructive iterative algorithm for learning half-spaces from informant.
New framework for ranking distributions using variable fractional parameters.
problem Ordering distributions with varying steepness and local non-concavities.
method Introducing a function γ:Ro[0,1] to replace the fixed parameter in fractional SD. result Enables ranking of a broader range of distributions and incorporates dynamic greediness.
Online class imbalance learning constitutes a new problem and an emerging research topic that focusses on the challenges of online learning under class imbalance and concept drift. Class imbalance deals with data streams that have very skewed distributions while concept drift deals with changes in the class imbalance s…
Recurrent Neural Networks (RNNs) are among the most popular models in sequential data analysis. Yet, in the foundational PAC learning language, what concept class can it learn? Moreover, how can the same recurrent unit simultaneously learn functions from different input tokens to different output tokens, without affect…
Unified framework for structured prediction with partial labelling.
problem Learning with partial labelling costs less but is not well studied.
method Structured prediction and infimum loss for a wide range of problems.
result Unified framework leads to explicit algorithms with statistical consistency.
While sparse inverse covariance matrices are very popular for modeling network connectivity, the value of the dense solution is often overlooked. In fact the L2-regularized solution has deep connections to a number of important applications to spectral graph theory, dimensionality reduction, and uncertainty quantificat…
New depth function for partial orders helps compare machine learning algorithms.
problem Comparing machine learning algorithms using non-standard data types.
method Adapted simplicial depth to partial orders, using ufg depth for comparison.
result Demonstrates promising variety of analysis approaches based on ufg methods.
DeepStreamCE detects new classes in streaming deep neural networks.
problem Detecting new classes in deep neural networks in a streaming environment.
method Uses autoencoder and MCOD stream-based clustering for real-time concept evolution detection.
result DeepStreamCE outperforms OpenMax in identifying concept evolution.
Evaluating, explaining, and visualizing high-level concepts in generative models, such as variational autoencoders (VAEs), is challenging in part due to a lack of known prediction classes that are required to generate saliency maps in supervised learning. While saliency maps may help identify relevant features (e.g., p…
Combines neural networks and expert rules for concept-based learning.
problem Extending concept-based learning with machine learning models.
method Form constraints for joint probability distribution and represent feasible set as a convex polytope.
result Neural networks can be trained to satisfy expert rules without violating them.