Advanced deep learning model improves speech enhancement by estimating phase accurately.
problem Difficulty in estimating the phase of clean speech in speech enhancement.
method Proposes Deep Complex U-Net, polar coordinate-wise complex-valued masking, and wSDR loss function.
result Achieves state-of-the-art performance in all metrics, outperforming previous approaches.
We develop and analyze efficient "coordinate-wise" methods for finding the leading eigenvector, where each step involves only a vector-vector product. We establish global convergence with overall runtime guarantees that are at least as good as Lanczos's method and dominate it for slowly decaying spectrum. Our methods a…
Proposes a new Armijo's condition for coordinate-wise functions.
problem Finding optimal step sizes in coordinate-wise optimization.
method Introduces a new Armijo's condition for functions defined on product spaces.
result Shows the advantage of the new condition over the standard Armijo's condition.
Proposes blockwise adaptive stepsize for faster training and better generalization in deep learning.
problem Widespread use of coordinate-wise adaptive methods like RMSprop and Adam leads to worse generalization than SGD.
method Splits network parameters into blocks and uses a blockwise adaptive stepsize, balancing adaptivity and generalization.
result Blockwise adaptive gradient descent converges faster and has lower generalization error than coordinate-wise adaptive methods.
Proposes a new Armijo's condition for general functions and provides an algorithm for its application.
problem Finding suitable step sizes for general functions in optimization.
method Introduces a coordinate-wise Armijo's condition and provides an algorithm to find suitable step sizes.
result Proves convergent results for various functions using the proposed algorithm.
PMI-Masking improves MLM pretraining by masking correlated spans efficiently.
problem Uniform token masking leads to inefficient and suboptimal performance in MLMs.
method PMI-Masking uses Pointwise Mutual Information to mask n-grams with high collocation.
result PMI-Masking reaches half the training time and improves performance.
AdaCliP reduces noise in private SGD training.
problem Privacy preserving machine learning over user data.
method Adaptive clipping of gradients to reduce noise in private SGD.
result AdaCliP adds less noise and improves model accuracy.
In this paper we study the fundamental problems of maximizing a continuous non-monotone submodular function over the hypercube, both with and without coordinate-wise concavity. This family of optimization problems has several applications in machine learning, economics, and communication systems. Our main result is the…
ST-MTM models complex time series by decomposing and masking seasonal and trend components.
problem Forecasting complex time series with intricate temporal variations.
method Seasonal-Trend Decomposition with Masking and Contrastive Learning.
result ST-MTM achieves superior forecasting performance compared to existing methods.
New algorithm resists up to half of Byzantine workers in distributed learning.
problem Resilience of distributed SGD in the presence of Byzantine attackers.
method Lipschitz-inspired coordinate-wise median approach (LICM-SGD).
result LICM-SGD can resist up to half of Byzantine workers in non-convex settings.
Expands MLM by masking token positions, improving performance and convergence.
problem Improving language model performance and convergence.
method Masking token positions along with [MASK] tokens, using a fully connected classifier stage.
result Shows .3% improvement and 50% faster convergence for BERT Base with position masking.
SMART training improves mask-predict translations.
problem Closing the performance gap between semi-autoregressive and autoregressive models.
method SMART training method for conditional masked language models.
result SMART-trained models produce higher-quality translations.
New method reduces diffusion model function evaluations for discrete data.
problem High computational burden in generating samples from masked diffusion models.
method Modified causal attention mask and speculative sampling mechanism for non-factorized predictions.
result Achieved ~2x reduction in required network forward passes.
Proposes a proportional masking strategy for better tabular data imputation.
problem Heterogeneity of tabular data disrupts uniform random masking in MAEs.
method Computes missingness statistics, generates proportional masks, uses MLP token mixing.
result Proportional masking preserves missingness distribution, improves imputation performance.
New analysis reveals masked self-supervised learning's effectiveness in extracting data structure.
problem Analyzing masked self-supervised learning in high-dimensional data.
method Developed precise high-dimensional analysis of masked modeling objectives.
result Identified phase transitions and structured regimes for masked self-supervised learning.
We classify the polar actions on the complex hyperbolic plane up to orbit equivalence. Apart from the trivial and transitive polar actions, there are five polar actions of cohomogeneity one and four polar actions of cohomogeneity two.
Study polar actions on Damek-Ricci spaces, proving existence and finding examples.
problem Characterize polar actions on Damek-Ricci spaces.
method Prove criteria for isometric actions to be polar, find examples, and classify actions.
result Non-trivial polar actions exist on all Damek-Ricci spaces.
The paper studies how Kähler polarizations degenerate to mixed polarizations on toric varieties.
problem Degeneration of Kähler polarizations to mixed polarizations on toric varieties.
method Constructing polarizations by Hamiltonian actions, finding one-parameter families of Kähler polarizations, and analyzing convergence of spaces of holomorphic sections.
result Kähler polarizations degenerate to mixed polarizations as k increases, with specific convergence results for one-parameter families. Polarized and G-polarized CR manifolds are smooth manifolds endowed with a double structure: a real foliation $\Cal F$ (given by the action of a Lie group G in the G-polarized case) and a transverse CR distribution (E,J). Polarized means that (E,J) is roughly speaking invariant by $\Cal F$. Both structures ar…
A polarity of a projective plane is a map, often assumed to be involutive, mapping a generic point to a generic line and reciprocally. The most classical polarity is the polarity with respect to a conic, but other exist: the harmonic polarity with respect to a triangle, the polarities with respect to high-degree algebr…
This paper connects masked pre-training to Bayesian model selection.
problem Understanding the success of masked pre-training and its generalization.
method The paper shows masked pre-training corresponds to maximizing the marginal likelihood.
result Masked pre-training with a suitable scoring function maximizes the marginal likelihood.
The generic fiber of a Lagrangian fibration on an irreducible holomorphic symplectic manifold is an abelian variety. Associate a polarization type to such Lagrangian fibrations coming from polarizations on a generic fiber. We prove that this polarization type is constant in families of Lagrangian fibrations. Further, w…
Optimizes pruning masks for neural networks using probabilistic fine-tuning and PAC-Bayes bounds.
problem Improving neural network performance through adaptive pruning of weights.
method Optimizes stochastic pruning masks by minimizing expected loss, considering data-adaptive regularization and feature alignment.
result Probabilistic fine-tuning leads to improved test error over baseline methods in neural networks.
We consider the problem of selecting an optimal mask for an image manifold, i.e., choosing a subset of the pixels of the image that preserves the manifold's geometric structure present in the original data. Such masking implements a form of compressive sensing through emerging imaging sensor platforms for which the pow…
Recent object detectors use four-coordinate bounding box (bbox) regression to predict object locations. Providing additional information indicating the object positions and coordinates will improve detection performance. Thus, we propose two types of masks: a bbox mask and a bounding shape (bshape) mask, to represent t…
Paper uses ResUNet-CMB to reconstruct cosmic polarization rotation from CMB data.
problem Reconstructing anisotropic cosmic polarization rotation from CMB data.
method Extended ResUNet-CMB to handle gravitational lensing and patchy reionization.
result ResUNet-CMB outperforms standard quadratic estimator in reconstructing all three effects.
Paper proposes a machine learning framework for VLSI mask optimization.
problem Costly VLSI mask optimization due to complex processes.
method Heterogeneous OPC framework using machine learning.
result Demonstrates efficiency and effectiveness of the proposed framework.
New method polarizes anisotropic Heisenberg groups.
problem Polarizing anisotropic Heisenberg groups.
method Implementing a technique to polarize anisotropic Heisenberg groups.
result New class of polarizable Carnot groups expanded.
The paper investigates the effects of invalid action masking in policy gradient algorithms.
problem Invalid actions in policy gradient algorithms can lead to suboptimal performance.
method The paper provides theoretical justification and empirical demonstrations of the importance of invalid action masking.
result Invalid action masking is crucial as the number of invalid actions increases.
The study introduces polarization of generalized Nijenhuis torsions and their relevance in operator fields.
problem Characterization of Haantjes C∞(M)-modules of operator fields. method Introducing polarization of generalized Nijenhuis torsions and proving algebraic identities.
result Polarizations of generalized Nijenhuis torsions are relevant in the characterization of Haantjes C∞(M)-modules of operator fields. Classifies polar foliations on symmetric spaces.
problem Classifying polar foliations on symmetric spaces.
method Orbit equivalence and classification up to codimension two.
result Foliations are either hyperpolar or extensions of rank one foliations.
Develops masks to explain neural network predictions.
problem Improving neural network interpretability for various applications.
method Creates explanation masks for pre-trained networks using a secondary network.
result Demonstrates the effectiveness of the method across different types of networks.
Assume that a projective variety together with a polarization is uniformly K-stable. If the polarization is canonical or anti-canonical, then the projective variety is uniformly K-stable with respects to any polarization sufficiently close to the original polarization.
Classifies totally geodesic submanifolds and polar actions on Stiefel manifolds.
problem Classifying totally geodesic submanifolds and polar actions on Stiefel manifolds.
method Classification through polar actions and cohomogeneity-one actions.
result Classification of orbits of polar actions on Stiefel manifolds.
Classifies hexagonal circular 3-webs with cubic polar curves.
problem Classifying hexagonal circular 3-webs with algebraic polar curves of degree three.
method Analyzes hexagonal circular 3-webs on unit sphere with polar points on a twisted cubic.
result Completes the classification of hexagonal circular 3-webs with algebraic polar curves of degree three.
The main result of this paper is that a polar action on a compact irreducible homogeneous Kaehler manifold is coisotropic. This is then used to give new examples of polar actions and to classify coisotropic and polar actions on quadrics.
Improved YOLOv5 model detects mask-wearing with enhanced accuracy.
problem Detecting mask-wearing in high traffic public places.
method Improved YOLOv5l with Multi-Head Attentional Self-Convolution, Swin Transformer Block, I-CBAM module, and enhanced feature fusion.
result 1.1% improvement in mAP(0.5) and 1.3% improvement in mAP(0.5:0.95) compared to YOLOv5l.
POLAR framework interprets word embeddings using polar opposites.
problem Lack of interpretability in pre-trained word embeddings.
method Adopt semantic differentials and polar opposites to transform embeddings.
result Interpretable word embeddings maintain performance comparable to original embeddings.
Simplified masked diffusion models improve discrete data generation.
problem Complex model formulations and unclear relationships hinder discrete data generative modeling.
method Developed a simple and general framework for masked diffusion models.
result Models trained on OpenWebText surpass prior diffusion language models and outperform autoregressive models.
Study empty polar varieties' impact on singular function-germs.
problem Topology of singular function-germs with nonisolated singularities.
method Analysis of empty polar varieties.
result Topology implications of nonempty polar varieties.
Language models trained on chess board states outperform those on moves, even with causal masking.
problem Applying causal masking to spatial data for training unimodal language models.
method Trained bidirectional and causal self-attention models on both spatial (board-based) and sequential (move-based) chess data.
result Models trained on spatial board states achieve stronger playing strength than those trained on sequential data, even with causal masking.
For complex projective manifolds we introduce polar homology groups, which are holomorphic analogues of the homology groups in topology. The polar k-chains are subvarieties of complex dimension k with meromorphic forms on them, while the boundary operator is defined by taking the polar divisor and the Poincare residue …
Totally geodesic sections found in polar actions.
problem Understanding sections of polar actions on Riemannian manifolds.
method Elementary proof of a folklore result.
result Sections of polar actions are totally geodesic.
The imbalance of buying and selling functions profoundly in the formation of market trends, however, a fine-granularity investigation of the imbalance is still missing. This paper investigates a unique transaction dataset that enables us to inspect the imbalance of buying and selling on the man-times level at high freq…
We prove a criterion for an isometric action of a Lie group on a Riemannian manifold to be polar. From this criterion, it follows that an action with a fixed point is polar if and only if the slice representation at the fixed point is polar and the section is the tangent space of an embedded totally geodesic submanifol…
Masking diffusion outperforms other discrete diffusion models by incorporating jump times into the model.
problem Improving the performance of discrete diffusion models.
method Conditioning on the jump schedule of discrete Markov processes.
result Schedule-conditioned discrete diffusion (SCUD) models outperform classical and masking diffusion models.
We show that simply connected Riemannian homogeneous spaces of compact semisimple Lie groups with polar isotropy actions are symmetric, generalizing results of Fabio Podesta and the third named author. Without assuming compactness, we give a classification of Riemannian homogeneous spaces of semisimple Lie groups whose…
Carnot groups can be polarized if they have specific coordinate systems.
problem Understanding when Carnot groups can be polarized.
method Proving Carnot groups with certain coordinate systems are polarizable.
result Carnot groups with suitable horizontal polar coordinates are polarizable.