Study investigates impact of labeler socio-cultural background on affect detection model performance.
problem Impact of labeler socio-cultural background on affect detection model performance.
method Investigates the impact of labeler socio-cultural background on affect detection model performance.
result Differences in labeler background impact the performance of affect detection models.
FLOPART solves peak detection by creating accurate train and test set predictions.
problem Correctly detecting peaks in sequential data.
method Dynamic programming changepoint algorithm with zero train label errors.
result FLOPART provides highly accurate predictions on both train and test sets.
Refines neural network predictions using background knowledge for improved accuracy.
problem Compensate for lack of labeled data in neural networks.
method Introduces differentiable refinement functions and Iterative Local Refinement (ILR) algorithm to refine predictions efficiently and accurately.
result ILR finds competitive results in MNIST addition task and refines predictions on complex SAT formulas.
New algorithm improves interpretability in sequence classification.
problem Lack of human-independent interpretability metrics in sequence classification.
method Combines linear classifiers with background knowledge embeddings to create a new feature space.
result Preserves predictive power while delivering more interpretable models.
State-of-the-art pedestrian detection models have achieved great success in many benchmarks. However, these models require lots of annotation information and the labeling process usually takes much time and efforts. In this paper, we propose a method to generate labeled pedestrian data and adapt them to support the tra…
This research shows unsupervised GANs can perform object segmentation without labels.
problem Performing object segmentation without pixel or image-level labels.
method Used large-scale unsupervised GAN models to differentiate foreground from background.
result Demonstrated high-quality saliency masks and new state-of-the-art performance.
Paper presents a neural network for recognizing human activities from unlabeled sensor data.
problem Time-consuming annotation of sensor data for activity recognition.
method Attention-based convolutional neural network for weakly labeled data.
result Attention model improves accuracy in recognizing human activities.
This paper frames causal structure estimation as a machine learning task. The idea is to treat indicators of causal relationships between variables as `labels' and to exploit available data on the variables of interest to provide features for the labelling task. Background scientific knowledge or any available interven…
We present supersymmetric, curved space, quantum mechanical models based on deformations of a parabolic subalgebra of osp(2p+2|Q). The dynamics are governed by a spinning particle action whose internal coordinates are Lorentz vectors labeled by the fundamental representation of osp(2p|Q). The states of the theory are t…
New GANs learn clean labels from noisy data.
problem Training GANs with noisy labels.
method Incorporating a noise transition model to learn clean label distributions.
result rGANs can learn clean label distributions from noisy labels.
Proposes a method to identify relevant genes in autism-related diseases using auxiliary information.
problem Identifying relevant genes in autism-related diseases from diverse data sources.
method Uses logistic regression to filter irrelevant genes and clusters relevant genes into cohesive groups using adjacency matrix.
result Superior performance and robustness in finite samples observed in simulation studies.
Researchers compare two methods for handlebody constructions, finding they are related with a 'background charge'.
problem Comparing two methods for handlebody constructions in finite ribbon categories.
method Admissible skein module construction vs. ansular functor construction.
result An isomorphism between the two constructions is proven, with a 'background charge' that becomes trivial in the unimodular case.
NURD improves model performance by distilling representations independent of nuisance variables.
problem Models trained under spurious correlations may fail on data with different nuisance-label relationships.
method Developed Nuisance-Randomized Distillation (NURD) to find representations independent of nuisance variables.
result NURD finds representations that perform better regardless of nuisance-label relationships.
Proposes FSM-IRL to learn invariant network representations considering feature and structural shifts.
problem Spatial heterogeneity and temporal dynamics lead to OOD generalization issues in geographic networks.
method Introduces FSM-IRL model that accounts for feature and structural distribution shifts using causal attention and reweighting.
result Demonstrates strong learning capabilities on geographic and social network datasets in OOD scenarios.
A new method for multi-label image classification using multiple feature views.
problem Limited by single-view feature, traditional matrix completion struggles with multi-label image classification.
method Multi-View Matrix Completion (MVMC) framework, combining weighted MC outputs from different views, using cross-validation for weights.
result MVMC framework improves multi-label image classification by exploiting complementary properties of different features and consistent labels.
New methods detect targets from imprecisely labeled hyperspectral data.
problem Challenges in acquiring labeled hyperspectral data.
method Multi-Target MI-ACE and MI-SMF methods that learn target signatures from imprecisely labeled samples.
result Effective at learning target signatures and performing target detection.
New method recovers predictions from unobservable source subpopulation in binary classification.
problem Challenging binary classification with unobservable subpopulation in source domain.
method Distribution matching method to estimate subpopulation proportions, rigorous derivation of prediction models.
result Our method outperforms naive benchmarks in synthetic and real-world datasets.
We consider bosonic supersymmetric backgrounds of ten-dimensional conformal supergravity. Up to local conformal isometry, we classify the maximally supersymmetric backgrounds, determine their conformal symmetry superalgebras and show how they arise as near-horizon geometries of certain half-BPS backgrounds or as a plan…
Machine-learned anomaly detection in new-physics searches needs calibration and look-elsewhere correction
problem Machine-learned anomaly detection in new-physics searches
method Conformal prediction layer
result Calibrated significance with distribution-free guarantees
Derives path-integrals for superstrings on curved backgrounds using string geometry theory.
problem Calculating path-integrals for superstrings on curved backgrounds.
method Derives path-integrals from string geometry theory by considering fluctuations around string backgrounds.
result Derives path-integrals for perturbative superstrings on all string backgrounds.
Derives path integrals for perturbative strings on various backgrounds.
problem Calculating path integrals for strings on curved backgrounds.
method Derives path integrals from string geometry theory by considering fluctuations around string backgrounds.
result Derives path integrals of all order perturbative strings on various backgrounds.
The study explores highly supersymmetric backgrounds in 11D supergravity.
problem Understanding and constructing highly supersymmetric backgrounds in 11D supergravity.
method Definition of abstract symbols and a strong version of the Reconstruction Theorem, proposing a strategy to construct backgrounds, and providing an example with detailed computation.
result Bijective correspondence between highly supersymmetric backgrounds and abstract symbols, and a classical supersymmetry gap result.
We examine how generalised geometries can be associated with a labelled Dynkin diagram built around a gravity line. We present a series of new generalised geometries based on the groups Spin(d,d)×R+ for which the generalised tangent space transforms in a spinor representation of the group. In …
We describe the construction of a Lie superalgebra associated to an arbitrary supersymmetric M-theory background, and discuss some examples. We prove that for backgrounds with more than 24 supercharges, the bosonic subalgebra acts locally transitively. In particular, we prove that backgrounds with more than 24 supersym…
UAED discovers adaptive environments for robust learning.
problem Avoiding spurious correlations in data.
method Unified framework that learns a distribution over data transformations.
result Improves worst-case accuracy on standard benchmarks.
New framework uses background knowledge to speed up causal discovery.
problem Scalable causal discovery for large datasets.
method Utilizes background knowledge during causal discovery process.
result Background knowledge reduces computational requirements and improves structure quality.
SRTC model for background/foreground separation with missing pixels.
problem Background/foreground separation with missing pixels in videos.
method Smooth robust tensor completion (SRTC) model with tensor proximal alternating minimization (tenPAM).
result Global convergence guarantee for the proposed algorithm.
Study optimal reinsurance for insurers with a reinsurer's default risk.
problem Optimal reinsurance for insurers with a reinsurer's default risk.
method Analytical solution for two types of reinsurance contracts.
result Joint effect of reinsurer's default and background risk on reinsurance demand.
We extend the Falceto-Zambon version of Marsden-Ratiu Poisson reduction to Poisson quasi-Nijenhuis structures with background on manifolds. We define gauge transformations of Poisson quasi-Nijenhuis structures with background, study some of their properties and show that they are compatible with reduction procedure. We…
Motivated by the search for new gravity duals to M2 branes with N>4 supersymmetry --- equivalently, M-theory backgrounds with Killing superalgebra osp(N∣4) for N>4 --- we classify homogeneous M-theory backgrounds with symmetry Lie algebra so(n)⊕so(3,2) for n=5,6,7. We f…
We explore all warped AdS4×wMD−4 backgrounds with the most general allowed fluxes that preserve more than 16 supersymmetries in D=10- and 11-dimensional supergravities. After imposing the assumption that either the internal space MD−4 is compact without boundary or the isometry algebra of the back…
New methods detect objects in industrial settings with little training data.
problem Lack of training data limits object detection in industrial settings.
method Adapted Faster R-CNN and Scaled Yolov4-p5 architectures for small training data.
result Both models can distinguish unknown objects from homogeneous backgrounds.
Generative Adversarial Networks generate PXD background noise efficiently.
problem Efficiently generate statistically independent PXD background noise samples.
method Conditional Generative Adversarial Networks (GANs) with contrastive learning.
result On-demand PXD background generator reduces storage requirements.
Heterotic backgrounds described using generalised geometry, preserving minimal supersymmetry.
problem Characterizing heterotic backgrounds preserving minimal supersymmetry in four dimensions.
method Using generalised geometry, characterizing backgrounds by an SU(3)imesSpin(6+n) structure and an involutive subbundle of the generalised tangent bundle. result The analysis of infinitesimal deformations reproduces known cohomologies of massless moduli.
Background doesn't affect personality predictions in deep networks.
problem Understanding how background images influence personality attribution in deep learning models.
method Explicitly studied the effect of background images on personality prediction in deep residual networks, controlling for confounds.
result Adding background information to input decreases model performance for personality trait prediction.
An approach for learning ancestral causal relationships in high dimensions, validated on human genome-wide data.
problem Learning ancestral causal relationships in high-dimensional biological data.
method Supervised learning approach with discrete indicators treated as labels, scalable to large problems.
result The approach is highly effective and scalable to the human genome-wide setting, robust to perturbations of input information.
Background: In this paper we present the approaches and methods employed in order to deal with a large scale multi-label semantic indexing task of biomedical papers. This work was mainly implemented within the context of the BioASQ challenge of 2014. Methods: The main contribution of this work is a multi-label ensemble…
Bayesian methods improve text annotation quality.
problem Inconsistent and unreliable human annotations in natural language processing.
method Two semi-supervised Bayesian methods: a deep learning model and an ensemble method.
result Bayesian methods enhance the reliability and performance of BERT models.
Paper proposes a method to train ML on sPlot background data without negative weights.
problem Training machine learning on data with sPlot background subtraction leads to negative weights and algorithm divergence.
method Proposes a rigorous mathematical approach to handle negative weights in sPlot background data.
result Allows the use of any machine learning method on sPlot background data samples without encountering negative weights.
Lectures detail field theory dynamics and exact WKB analysis.
problem Understanding quantum field theories with four supercharges.
method Combining WKB analysis with 2D quantum field theories.
result Partition function characterizes non-perturbative dynamics.
The paper examines how background risk affects portfolio selection and optimal reinsurance design.
problem Maximizing the probability of reaching a financial goal in the presence of background risk.
method Quantile formulation method to derive optimal solutions explicitly.
result The presence of background risk does not change the solution shape but alters the parameter values.
We prove that supersymmetry backgrounds of (1,0) and (2,0) six-dimensional supergravity theories preserving more than one half of the supersymmetry are locally homogeneous. As a byproduct we also establish that the Killing spinors of such a background generate a Lie superalgebra.
Investment models account for both probabilistic and possibilistic risks.
problem Investment and background risks are modeled probabilistically and possibilistically.
method Developed three investment models combining probabilistic and possibilistic risks.
result Approximate calculation formula for optimal investment solutions proved.
In this paper we study homogeneous backgrounds of type IIB supergravity where the underlying geometry is that of a symmetric space. We determine which ten-dimensional lorentzian symmetric spaces (up to local isometry) admit such backgrounds and in about two thirds of the cases we determine fully their moduli space.
Defines Killing spinors and bosonic backgrounds in 5D supergravity.
problem Characterizing backgrounds in 5D supergravity.
method Calculates Spencer cohomology, defines Killing spinors, and imposes constraints on spinor connection curvature.
result Recover field equations of 5D supergravity and find new field equations for sp(1)-valued one-form. PCA++ improves robustness to background noise in contrastive learning.
problem Recovering shared signal subspaces from positive pairs in high-dimensional data with structured background noise.
method PCA++ uses hard uniformity-constrained contrastive learning to enforce identity covariance on projected features.
result PCA++ outperforms standard PCA and alignment-only PCA+ in simulations and real-world datasets.
We present two different families of eleven-dimensional manifolds that admit non-restricted extensions of the isometry algebras to geometric superalgebras. Both families admit points for which the superalgebra extends to a super Lie algebra; on the one hand, a family of N=1, ν=3/4 supergravity backgrounds a…
Method identifies causal drivers from background features.
problem Distinguishing causal influence from hidden confounding.
method Stability of regression coefficients measured by statistic V.
result V converges to zero if and only if no causal drivers exist.