A new method quantizes output space for multi-target regression.
problem Predicting multiple continuous targets using shared predictors.
method MRQ method that quantizes output space to model dependencies and scale.
result MRQ achieves high scalability and competitive accuracy.
Develops G-MLKM for better data-target association in constrained spaces.
problem Data-target association problem in constrained spaces with limited sensor information.
method Graph-based multi-layer k-means++ (G-MLKM) method, including MLKM for local space and G-MLKM for general constrained space.
result Improves data-target association accuracy through error correction mechanisms.
New sigma models use (4,0) supersymmetry for hyperkähler target spaces.
problem Constructing sigma models with (4,0) off-shell supersymmetry. method Formulated (4,0) supermultiplets, constructed sigma models with hyperkähler target spaces. result Explicit construction of target space geometries using (4,0) supersymmetry. Survey on harmonic maps in non-smooth spaces, focusing on rigidity.
problem Rigidity phenomena in non-smooth spaces.
method Regularity theory of harmonic maps to non-smooth targets.
result Generalizations of Margulis superrigidity and holomorphic rigidity of Teichmüller space.
The study proves Liouville-type theorems and Bochner formulas for harmonic maps into CAT(κ) spaces.
problem Analyzing harmonic maps from Riemannian polyhedra into CAT(κ) spaces.
method Computing a target variation formula to derive Liouville-type theorems and Bochner formulas.
result Proves Liouville-type theorems and Bochner formulas for harmonic maps into CAT(1) spaces.
It is well-known that sigma-models with symmetric target spaces are classically integrable. At the example of the model with target space the flag manifold U(3)/U(1)^3 -- a non-symmetric space -- we show that the introduction of torsion allows to cast the equations of motion in the form of a zero-curvature condition fo…
We study a formulation of the standard Poisson sigma model in which the target space Poisson manifold carries the Hamilton action of some finite dimensional Lie algebra. We show that the structure of the action and the properties of the gauge invariant observables can be understood in terms of the associated target spa…
The paper establishes new Casorati inequalities for various Riemannian maps and submersions.
problem Developing new inequalities for Riemannian maps and submersions.
method Using general forms of Casorati inequalities, the paper derives inequalities for specific Riemannian spaces.
result The paper provides new Casorati inequalities for Riemannian maps and submersions.
A new method debiases multiple target parameters without IFs.
problem Debiasing multiple target parameters in nonparametric models.
method Kernel Debiased Plug-in Estimation (KDPE) using TMLE and reproducing kernel Hilbert spaces.
result KDPE simultaneously debiases all pathwise differentiable target parameters.
We study the propagation of bosonic strings in singular target space-times. For describing this, we assume this target space to be the quotient of a smooth manifold M by a singular foliation F on it. Using the technical tool of a gauge theory, we propose a smooth functional for this scenario, such that the p…
ReTaSA tackles continuous target shift in regression problems.
problem Continuous target shift in regression settings.
method Nonparametric regularized approach to estimate importance weight function.
result The method provides theoretical justification for the estimated importance weight function.
The paper introduces a new Gaussian Process model that learns target variance in multi-modal data.
problem Learning target variance in multi-modal data distributions.
method The approach involves metric learning over data centers, each with its own kernel metric and precision matrix.
result The model demonstrates improved reliability in learning target variance in multi-modal data.
New method flattens decision boundary by targeting shortcut-aligned axes in disentangled latent space.
problem Shortcut learning in neural networks, leading to poor out-of-distribution generalization.
method Injects targeted anisotropic noise to regularize classifier sensitivity along shortcut-aligned axes.
result Achieves state-of-the-art OOD performance without shortcut labels or conflicting samples.
Gradient descent reshapes the function space of neural networks.
problem Understanding how feature learning affects the function space of neural networks.
method Characterized the evolution of the feature space during training using a two-layer neural network.
result Gradient descent induces a data-adaptive deformation that selectively enhances signal-aligned directions.
Unified CLIP space manipulations improve GAN adaptation with a single target image.
problem Overfitting or underfitting in fine-tuning a pre-trained generator with a single target image.
method Two-step training strategy: latent optimization in CLIP space followed by generator fine-tuning with CLIP space consistency loss.
result Our model generates diverse outputs with the target texture and outperforms baseline models.
In this work, we propose a novel node splitting method for regression trees and incorporate it into the regression forest framework. Unlike traditional binary splitting, where the splitting rule is selected from a predefined set of binary splitting rules via trial-and-error, the proposed node splitting method first fin…
We study a sigma-model with target space the flag manifold U(3)/U(1)^3. A peculiarity of the model is that the complex structure on the target space enters explicitly in the action. We describe the classical solutions of the model for the case when the worldsheet is a sphere CP^1.
A multi-step framework tackles online unsupervised domain adaptation with novel mean-target subspace computation.
problem Online unsupervised domain adaptation with unlabelled target data arriving sequentially.
method Multi-step framework with a novel mean-target subspace computation and temporal coherency consideration.
result Improved performance over previous approaches on four datasets.
PGA maps data and target distributions to a latent space for better generative model training.
problem Training generative models is difficult due to mismatch between data and target distributions.
method Train generator to match target distribution in latent space using autoencoder.
result PGA achieves state-of-the-art FID scores on CIFAR-10 and CelebA.
In this paper we provide examples of maps from almost complex domains into pseudo-Riemannian symmetric targets, which are pluriharmonic and not integrable, i.e. do not admit an associated family. More precisely, for one class of examples the source has a non-integrable complex structure, like for instance a nearly Kaeh…
In this paper, we propose a novel learning framework for the problem of domain transfer learning. We map the data of two domains to one single common space, and learn a classifier in this common space. Then we adapt the common classifier to the two domains by adding two adaptive functions to it respectively. In the com…
Adaptive algorithm for online evaluation of targeted audiences in advertising.
problem Determining the right match between advertising creatives and target audiences.
method Contextual bandit approach to address audience overlap and learn optimal display policies.
result The proposed method is more efficient than traditional split-testing methods.
LEARNER improves low-rank matrix estimation using source population data.
problem Improving low-rank matrix estimation in target populations with diverse data sources.
method LEARNER uses similarity in latent spaces between source and target populations to enhance estimation.
result LEARNER often outperforms benchmark methods, especially with higher signal-to-noise ratios in the source population.
New analysis of Langevin Monte Carlo via convex optimization.
problem Sampling from logconcave smooth and non-smooth target distributions.
method Formulation as a convex optimization problem, analysis using convex optimization techniques.
result Non-asymptotic analysis of Unadjusted Langevin Algorithm and new sampling methods.
A Kernel Adaptive Metropolis-Hastings algorithm is introduced, for the purpose of sampling from a target distribution with strongly nonlinear support. The algorithm embeds the trajectory of the Markov chain into a reproducing kernel Hilbert space (RKHS), such that the feature space covariance of the samples informs the…
RL approach for target tracking with unknown dynamics and sensor control.
problem Tracking an unknown target with sensor control.
method Track-MDP formulation for RL, compared with POMDP.
result Optimal RL policy tracks all target paths with certainty.
The Poisson--Weil sigma model, worked out by us recently, stems from gauging a Hamiltonian Lie group symmetry of the target space of the Poisson sigma model. Upon gauge fixing of the BV master action, it yields interesting topological field theories such as the 2--dimensional Donaldson-Witten topological gauge theory a…
For a germ of a smooth map f and a subgroup G_V of any of the Mather groups G for which the source or target diffeomorphisms preserve some given volume form V in the source or in the target we study the G_V-moduli space of f that parameterizes the G_V-orbits inside the G-orbit of f. We find, for example, that this modu…
Study on reliability of latent reuse in diffusion models under distribution shift.
problem When can latent spaces from a source dataset be reused for a target dataset with different distributions?
method Considered a source-target setting with approximately low-dimensional datasets near different subspaces. Analyzed the target-domain score error due to principal-angle misalignment and target ambient noise.
result Latent reuse is reliable only if the source and target subspaces are close and the target ambient noise is not too amplified.
Study Liouville theorems for harmonic maps along ancient super Ricci flows.
problem Proving Liouville theorems for harmonic maps under specific geometric conditions.
method Using Perelman's reduced geometric viewpoint, derive Liouville theorems with controlled growth.
result Sharp growth conditions and new Liouville theorems for both non-positively and positively curved target spaces.
New method optimizes neural network learning by adjusting random parameters to target function features.
problem Difficulty in setting optimal random parameters for neural network learning.
method Adjusts sigmoid slopes and positions to target function features in a randomized learning method.
result Significantly better approximation of complex target functions compared to standard methods.
This paper tackles G-ZSL by learning compositional spaces to classify unseen classes.
problem Classifying unseen classes in a test set.
method Space decomposition method to estimate and fine-tune decision boundaries between source and target classes.
result State-of-the-art performance on multiple G-ZSL benchmarks.
Proves existence of optimal shallow neural networks with ReLU activation.
problem Proving the existence of optimal shallow feedforward networks with ReLU activation.
method Proves existence of global minima in the loss landscape for continuous target functions using shallow feedforward neural networks with ReLU activation.
result Existence of global minima in the loss landscape for shallow feedforward networks with ReLU activation.
Wave maps into negatively curved targets can blow up stably.
problem Existence and stability of blowup for wave maps.
method Construction of a self-similar wave map for a negatively curved target.
result Stable blowup mechanism for wave maps in high dimensions.
This paper tackles UDA by learning domain-invariant embeddings using distribution alignment and pseudo-labels.
problem Unsupervised domain adaptation between two visual domains.
method Shared deep encoder, Sliced-Wasserstein Distance, deep classifier, pseudo-labels for class alignment.
result Effective solution for training deep classification networks on source domain to generalize to target domain.
A new method improves target selection for manipulating complex systems like the brain.
problem Improper incorporation of low-variance outcomes into latent space of predictive models.
method Developed a novel objective based on supervised variational autoencoders (SVAEs) for PPCA (Probabilistic Principal Component Analysis).
result gPCR (Generative Principal Component Regression) dramatically improves target selection in manipulation compared to standard PCR and SVAEs.
We study the problem of unsupervised domain adaptation, which aims to adapt classifiers trained on a labeled source domain to an unlabeled target domain. Many existing approaches first learn domain-invariant features and then construct classifiers with them. We propose a novel approach that jointly learn the both. Spec…
A generic smooth map of a closed 2k-manifold into (3k−1)-space has a finite number of cusps (Σ1,1-singularities). We determine the possible numbers of cusps of such maps. A fold map is a map with singular set consisting of only fold singularities (Σ1,0-singularities). Two fold maps are fold bordant if the…
Classifies two-dimensional extended homotopy field theories with aspherical targets.
problem Classifying two-dimensional extended homotopy field theories with aspherical targets.
method Defining and classifying E-HFTs with specific properties and using Frobenius algebras.
result Classifying E-HFTs taking values in symmetric monoidal bicategories of algebras and bimodules.
Generically learns movement control policies from exploration data.
problem Movement optimization in physically based characters.
method Parameterizes actions as target states, learns low-level control policy.
result Improves movement optimization across multiple tasks and algorithms.
This paper tackles target-dependent label complexity gap in active learning.
problem Target-dependent label complexity gap in Agnostic Active Learning.
method Introduces a novel distribution-splitting strategy based on number density to reduce label complexity and error rate.
result Provides theoretical guarantees and practical advantages for reducing label complexity and error rate.
The paper provides theoretical insights into deep domain adaptation.
problem Closing the gap between source and target domains in deep domain adaptation.
method A rigorous framework to explain transfer learning and minimize loss.
result First theoretical result characterizing joint space and transfer learning gain.
Deep generative model discovers inhibitors for unknown targets.
problem Discovering novel inhibitor molecules for unknown drug targets.
method Deep generative framework trained on protein sequences, small molecules, and interactions.
result Micromolar-level inhibition observed for two out of four synthesized candidates, including activity against SARS-CoV-2 variants.
Framework verifies global correctness of neural networks for perception tasks.
problem Verifying robustness of neural networks is insufficient; global correctness needs to be ensured.
method Specified a state space and observation process to define the target input space. Tiled the spaces and compared ground truth and network output bounds to deliver error bounds.
result Framework can verify error bounds globally over the target input space and detect illegal inputs.
Improves probability distribution compression with KT algorithm.
problem Efficiently compressing probability distributions.
method Kernel thinning (KT) algorithm with four improvements.
result KT yields tighter, dimension-free guarantees for any kernel.
Reviews uses of nonlinear sigma models in various systems.
problem Understanding nonlinear sigma models in different physical contexts.
method General discussion and focus on geometrical interpretations.
result Connection between sigma models and various geometries.
SIXO improves inference by learning smoothing distributions from all observations.
problem Inference limitations due to ignoring future observations in filtering distributions.
method Density ratio estimation to warp filtering distributions into smoothing distributions, then use SMC with learned targets.
result Proves tighter log marginal lower bounds and more accurate inferences and estimates.
We explore the nonperturbative aspects of the chiral algebras of N = (0,2) sigma models, which perturbatively are intimately related to the theory of chiral differential operators (CDOs). The grading by charge and scaling dimension is anomalous if the first Chern class of the target space is nonzero. This has some nont…