GIRNet tackles multi-tasking with mixed domain sequences, improving sentiment and tagging tasks.
problem Labeling sequences with mixed domain data and position-specific inference.
method Unified position-sensitive multi-task RNN architecture with gated state sequences from auxiliary data.
result GIRNet achieves new state-of-the-art performance in sentiment classification, POS tagging, and target position-sensitive annotation.
Self-regulation improves sequence-to-sequence learning by choosing feedback types.
problem Different types of feedback have varying costs and effects on learning.
method Self-regulation strategies decide when to ask for different types of feedback.
result Self-regulator discovers optimal cost-quality trade-off by mixing feedback types.
Paper analyzes distributed learning with non-i.i.d. samples.
problem Learning rate analysis for distributed kernel ridge regression with dependent samples.
method Integral operator approach and covariance inequality for strong mixing sequences.
result Derives optimal learning rates for distributed kernel ridge regression.
The study explores splitting conditions for mixed braid group sequences.
problem Conditions for splitting the Fadell-Neuwirth short exact sequence in mixed braid groups.
method Analysis of mixed braid groups and their quotients, computation of specific groups.
result Conditions for the projection to admit a section, including divisibility conditions.
Concentration of infinitely exchangeable sequences with bounded-difference constants
problem Quantifying uncertainty in AI benchmarks
method Using a mixture-free Hoeffding-type bound
result Tight, mixture-free Hoeffding-type bound for zero-sum linear contrasts
i-Mix improves contrastive learning across domains without domain-specific augmentations.
problem Improving contrastive representation learning for unlabeled data across diverse domains.
method i-Mix treats contrastive learning as a non-parametric classifier problem, mixing data in input and virtual label spaces.
result i-Mix consistently improves representation quality across image, speech, and tabular data domains.
Data of practical interest - such as personal records, transaction logs, and medical histories - are sequential collections of events relevant to a particular source entity. Recent studies have attempted to link sequences that represent a common entity across data sets to allow more comprehensive statistical analyses a…
New method combines domain changes and sparse mixing for better latent variable learning.
problem Challenges in identifying latent variables due to insufficient domain changes and violated sparsity constraints.
method Combines sufficient changes and sparse mixing constraints, using domain encoding networks and variational autoencoders.
result Identifiability of latent variables achieved with less restrictive constraints.
MiVaBo optimizes mixed-variable functions efficiently, handling constraints.
problem Optimizing expensive, mixed-variable functions with discrete constraints.
method Combines linear surrogate model and Thompson sampling, optimizing acquisition function.
result First BO method to handle complex constraints over discrete variables.
A new distance for mixed-variable, hierarchical datasets with meta variables.
problem Heterogeneous datasets limit generalizability and performance in machine learning and optimization.
method Developed a modeling framework for mixed-variable and hierarchical domains with meta variables, and a novel distance function.
result The novel distance function allows comparison of heterogeneous datasets, improving model performance.
Mix-up domain adaptation improves dynamic RUL predictions across various conditions.
problem Dynamic RUL predictions under non-i.i.d conditions.
method Three-staged mechanism with mix-up strategy for source and target domains alignment, self-supervised learning.
result MDAN outperforms existing methods in 12 out of 12 cases for dynamic RUL predictions.
Proposes a new RNN model for grouped sequential data with varying time intervals.
problem Implicitly models fixed time intervals between observations and lacks group-level effects.
method Mixed membership framework for RNN, learning group-level base parameter.
result Demonstrates dynamic topic modeling with evolving topic distributions over time.
Estimates missing mass in Markovian sequences with linear runtime and near-optimal risk.
problem Estimating missing mass in Markovian sequences.
method Windowed Good-Turing (WingIt) estimator.
result Risk decays as O ~ ( T m i x / n ) \widetilde{O}(\mathsf{T_{mix}}/n) O ( T mix / n ) , independent of state space size. Paper analyzes Nyström regularization for time series forecasting with sequential sub-sampling.
problem Learning rate analysis of Nyström regularization for τ τ τ -mixing time series. method Banach-valued Bernstein inequality and integral operator approach for τ τ τ -mixing sequences. result Almost optimal learning rates for Nyström regularization with sequential sub-sampling.
Estimates stationary mass and frequency from non-i.i.d. data.
problem Estimating stationary mass and frequency from non-i.i.d. data.
method Combines plug-in estimator with WingIt modification for exponentially α α α -mixing processes. result Universal consistency in n n n for total variation distance estimation. Branching Flows generates sequences of varying lengths using binary trees.
problem Generating sequences of unknown lengths or fixed elements.
method A generative modeling framework that evolves states over binary trees, controlling sequence length.
result Branching Flows can generate sequences of varying lengths and mix different types of state spaces.
Bayesian optimisation tackles high-dimensional categorical and mixed search spaces.
problem Bayesian optimisation on high-dimensional categorical and mixed search spaces is challenging.
method Combining local optimisation with a tailored kernel design.
result Empirically outperforms current baselines in performance and computational costs.
Research tackles novelty detection for mixed-type data, proposing probabilistic methods.
problem Detect anomalies in mixed-type datasets like numerical and categorical data.
method Experimental comparison of methods, probabilistic nonparametric model, autoencoder-based model.
result Developed robust methods for mixed-type data novelty detection.
Study online learning in RKHS with dependent processes, focusing on \(β\)- and \(φ\)-mixing.
problem Online learning in RKHS with dependent data.
method Online regularized learning algorithm in RKHS, analyzing \(β\)- and \(φ\)-mixing sequences.
result Probabilistic upper bounds and convergence rates for mixing coefficients.
Study LASSO for high-dimensional VAR models with weakly dependent innovations.
problem Understanding sparse regularization in high-dimensional VAR models with weakly dependent innovations.
method LASSO estimation for weakly sparse VAR models with heavy tailed innovations, under L 1 L^1 L 1 mixingale condition. result Oracle properties of LASSO estimation in high-dimensional VAR models with weakly dependent innovations.
Parameterizing the approximate posterior of a generative model with neural networks has become a common theme in recent machine learning research. While providing appealing flexibility, this approach makes it difficult to impose or assess structural constraints such as conditional independence. We propose a framework f…
DSSM separates domain-invariant dynamics from domain-specifics in sequential data.
problem Learning cross-domain sequence representations from diverse data domains.
method Introduce disentangled state space models (DSSM) using unsupervised VAE-based training.
result Improves knowledge transfer and robust prediction across domains.
We provide a measure based topology for certain unions of C2 rectifiable submanifolds of mixed dimensions in Rn. In this topology lower dimensional sets remain in the limit as measures when higher dimensional sets collapse down to them. For example a decreasing sequence of spheres may have a limit consisting of just a …
Reinforcement learning after next-token prediction aids in learning from diverse sequence lengths.
problem Learning from sequences of varying lengths and complexity.
method Introducing a framework to study reinforcement learning with autoregressive transformers, focusing on next-token prediction and mixture distributions of short and long sequences.
result Reinforcement learning after next-token prediction enables autoregressive transformers to generalize from long sequences, even when they are rare.
While all kinds of mixed data -from personal data, over panel and scientific data, to public and commercial data- are collected and stored, building probabilistic graphical models for these hybrid domains becomes more difficult. Users spend significant amounts of time in identifying the parametric form of the random va…
Paper describes links of mixed polynomials with specific properties.
problem Understanding the links of mixed polynomials with nice Newton boundaries.
method Analyzes links constructed from sequences of links associated with compact 1-faces of the Newton boundary.
result Links of singularities of inner non-degenerate mixed polynomials can be described using a specific procedure.
The paper studies invariant weighted Bergman metrics on domains.
problem Investigating invariant weighted Bergman metrics under biholomorphisms.
method Introducing invariant weight assignments, using Bergman's minimum integral method and domain version of Tian-Yau-Zelditch expansion.
result Uniform convergence of weighted Bergman kernels and metrics on uniform squeezing domains.
MOCA-HESP optimizes high-dimensional combinatorial and mixed spaces using hyper-ellipsoid partitioning.
problem Challenges in optimizing high-dimensional, combinatorial and mixed spaces.
method MOCA-HESP uses hyper-ellipsoid space partitioning with different categorical encoders and multi-armed bandit for adaptive selection.
result MOCA-HESP outperforms existing methods on various synthetic and real-world benchmarks.
New method uses dendrograms for better mixture model selection and clustering.
problem Selecting the correct number of components in finite mixture models.
method Hierarchical clustering tree derived from overfitted latent mixing measures.
result Consistently selects the true number of mixing components and optimal convergence rate for parameter estimation.
This paper shows that, in dimensions two or more, there are no holomorphic isometries between Teichmüller spaces and bounded symmetric domains in their intrinsic Kobayashi metrics.
This paper tackles convex-submodular minimax problems in mixed continuous-discrete domains.
problem Convex-submodular minimax problems in mixed continuous-discrete domains.
method Introduces new notions of optimality and proposes iterative algorithms combining discrete and continuous optimization.
result Characterizes convergence rates, computational complexity, and quality of solutions for convex and monotone-submodular minimax problems.
Paper introduces MSA for weakly supervised covariance alignment in MEG signals.
problem Limited labeled signals in target datasets for MEG applications.
method Mixing model Stiefel Adaptation (MSA) leveraging unlabeled data.
result MSA outperforms recent methods in brain-age regression with MEG signals.
Paper solves a mixed boundary value problem in space forms with umbilical boundaries.
problem Solving a partially overdetermined mixed boundary value problem in space forms.
method Generalizing previous results to domains with partial umbilical boundaries.
result A partially overdetermined problem in a domain with partial umbilical boundary admits a solution if and only if the rest part of the boundary is also part of an umbilical hypersurface.
Characterizes measures preserving compound mixed renewal process properties.
problem Preserving compound mixed renewal process properties under different probability measures.
method Characterization of progressively equivalent probability measures.
result Any compound mixed renewal process can be converted into a compound mixed Poisson process through a change of measures.
Hot spots conjecture proven for small eigenvalue domains.
problem Hot spots conjecture for hyperbolic planar domains with small eigenvalues.
method Proved a variant of Rauch's hot spots conjecture.
result Second Neumann Laplace eigenfunctions have no interior critical points on large convex domains.
Identifying important components or factors in large amounts of noisy data is a key problem in machine learning and data mining. Motivated by a pattern decomposition problem in materials discovery, aimed at discovering new materials for renewable energy, e.g. for fuel and solar cells, we introduce CombiFD, a framework …
Rapid mixing of Langevin dynamics on Riemannian manifolds
problem Mixing time of Langevin dynamics on Riemannian manifolds
method Relation between Langevin processes in domain and image
result Achievable polynomial mixing times
New framework infers causal shifts in event sequences under out-of-domain interventions.
problem Inferring causal relationships in event sequences without considering out-of-domain interventions.
method Proposes a new causal framework to define ATE, designs an unbiased ATE estimator, and uses a Transformer-based neural network model.
result Demonstrates superior performance in ATE estimation and goodness-of-fit under out-of-domain-augmented point processes.
Transformer models show robustness across domains with domain adversarial training.
problem Domain adaptation from multiple sources with no labeled data.
method Domain adversarial training and mixture of experts.
result Domain adversarial training improves representation but not performance.
In this paper we present the construction of explicit quasi-isomorphisms that compute the cyclic homology and periodic cyclic homology of crossed-product algebras associated with (discrete) group actions. In the first part we deal with algebraic crossed-products associated with group actions on unital algebras over any…
Two algorithms learn Gaussian graphical models from Glauber dynamics trajectories, achieving optimal performance.
problem Learning Gaussian graphical models from a single trajectory of a dependent stochastic process.
method Two algorithms based on dueling-neighborhood search and local statistics built from the update sequence of Glauber dynamics.
result Achieve κ − 2 κ^{-2} κ − 2 dependence of the information-theoretic lower bounds, mixing-free and signal-optimal. We investigate properties of the Hodge metric of a mixed period domain. In particular, we calculate its curvature and the curvature of the Hodge bundles. We also consider when the pull back metric via a period map is Kähler. Several applications in cases of geometric interest are given, such as for normal functions and…
Method approximates Lipschitz domains with smoother shapes.
problem Approximating bounded Lipschitz domains.
method Sequence of smooth, bounded domains with weak curvatures.
result Uniform isocapacitary estimates for approximating sets.
A new perspective on self-attention models using MLPs.
problem Improving sequence modeling with self-attention mechanisms.
method Introducing HyperMLP and HyperGLU, which use dynamic two-layer MLPs with reverse-offset layout.
result HyperMLP/HyperGLU consistently outperform softmax-attention baselines.
Fewer data weight updates lead to faster convergence in machine learning models.
problem Improving robustness of machine learning models through data mixing.
method Analyzing convergence behavior of data mixing with a finite number of inner steps.
result The optimal number of inner steps scales with the budget and type of gradients used.
Inertial information processing plays a pivotal role in ego-motion awareness for mobile agents, as inertial measurements are entirely egocentric and not environment dependent. However, they are affected greatly by changes in sensor placement/orientation or motion dynamics, and it is infeasible to collect labelled data …
Paper extends nonparametric regression bounds for dependent β \beta β -mixing samples.
problem Analyzing error in nonparametric regression with dependent data.
method Extends uniform deviation inequalities from independent to dependent β \beta β -mixing samples. result Derives generalization bounds for nonparametric regression with dependent data.
Study limits of convex domains in projective plane, proving specific results.
problem Understanding limits of convex domains in projective plane.
method Analyzing sequences of properly convex domains with bounded multiplicity.
result Determined all Hausdorff limit domains after normalization.