Proposes PKM for soft K-means clustering.
problem Soft K-means (m=1) unsolved since 1981.
method Probabilistic K-Means (PKM) via nonlinear programming.
result Proposed methods solve PKM efficiently.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “active gradient projection”
Investigating the interaction between gradient-only line searches and different activation functionsstat.ML
GOLS finds activation functions affect training robustness, especially ReLU.
problem Investigate how different activation functions impact GOLS in neural network training.
method Identify SNN-GPPs for GOLS, analyze activation function effects on gradient continuity.
result GOLS robust for most activation functions but sensitive to ReLU.
Soft-Radial Projection solves gradient saturation in constrained deep learning.
problem Gradient saturation in deep learning models when integrating hard constraints.
method Introduces Soft-Radial Projection, a differentiable layer that maps predictions onto constraint boundaries without rank-deficient Jacobians.
result Improves convergence and solution quality over state-of-the-art methods.
We explore a new approach for training neural networks where all loss functions are replaced by hard constraints. The same approach is very successful in phase retrieval, where signals are reconstructed from magnitude constraints and general characteristics (sparsity, support, etc.). Instead of taking gradient steps, t…
A new indicator measures project risk from activity durations.
problem Managing project risks throughout the lifecycle.
method Activity Risk Index (ARI) based on Schedule Risk Baseline.
result Identifies activities contributing most to project uncertainty.
Scientists and engineers rely on accurate mathematical models to quantify the objects of their studies, which are often high-dimensional. Unfortunately, high-dimensional models are inherently difficult, i.e. when observations are sparse or expensive to determine. One way to address this problem is to approximate the or…
FP uses random projections to train networks without feedback, achieving comparable performance to backpropagation.
problem Training neural networks without feedback from downstream layers.
method Forward Projection (FP) method that uses randomised nonlinear projections and closed-form regression.
result FP achieves comparable generalisation to backpropagation methods with a single forward pass, offering significant speedup.
Deep active subspaces - a scalable method for high-dimensional uncertainty propagationphysics.comp-ph
A problem of considerable importance within the field of uncertainty quantification (UQ) is the development of efficient methods for the construction of accurate surrogate models. Such efforts are particularly important to applications constrained by high-dimensional uncertain parameter spaces. The difficulty of accura…
Regularizing activations in neural networks via distribution matching with the Wasserstein metriccs.LG
Proposes PER loss to regularize neural network activations to normal distribution.
problem Improving neural network generalization and training speed.
method Regularizes activations to standard normal distribution via projected error function and Wasserstein distance.
result Minimizes Wasserstein distance between activation distribution and standard normal.
We introduce switched linear projections for expressing the activity of a neuron in a deep neural network in terms of a single linear projection in the input space. The method works by isolating the active subnetwork, a series of linear transformations, that determine the entire computation of the network for a given i…
New framework tackles high-dimensional reliability analysis using surrogate models and active subspaces.
problem High computational cost and curse of dimensionality in reliability analysis of high-dimensional systems.
method Sparse Active Subspace (SAS) algorithm for identifying low-dimensional manifolds and constructing efficient surrogate models.
result Proposed framework significantly improves accuracy and efficiency of reliability analysis compared to existing methods.
BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activationscs.LG
BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.
problem Gradient mismatch in BNNs due to binarizing activations.
method Using gradient of smoothed loss function to estimate gradient mismatch, proposing BinaryDuo scheme with coupled ternary activations.
result BinaryDuo outperforms state-of-the-art BNNs on various benchmarks.
Improved neural network training in low-dimensional random bases.
problem Inefficient optimization in large-scale neural networks.
method Re-draw random subspace at each training step, apply independent projections to different network parts.
result Significantly better optimization performance and efficiency.
Paper tackles active labeling for partial supervision.
problem Accessing stochastic gradients with partial supervision.
method Streaming technique to minimize generalization error.
result Proves minimization of generalization error ratio.
Warm-start strategies speed up GP inference by 19x.
problem Efficient sequential inference in Gaussian processes.
method Three warm-start strategies exploiting smaller linear systems.
result Warm-starting achieves up to 19x speed-up in convergence.
Sigmoid-type networks avoid vanishing gradients with regularization and rescaling.
problem Vanishing gradients in sigmoid-type networks.
method Mathematical arguments and two remedies: regularization and rescaling.
result Demonstrates effectiveness of regularization and rescaling in practice.
We propose a method to impose homogeneous linear inequality constraints of the form on neural network activations. The proposed method allows a data-driven training approach to be combined with modeling prior knowledge about the task. One way to achieve this task is by means of a projection step at test time…
This paper analyzes and improves active learning techniques for real-world projects.
problem Reducing labelling effort in machine learning models with real-world constraints.
method Systematic study of active learning issues, proposing techniques to address model convergence, annotation error, and dataset imbalance.
result Presentation of two techniques to speed up active learning: partial uncertainty sampling and larger query size.
Generalizes NTK for surrogate gradient learning in neural networks.
problem Lack of theoretical foundation for surrogate gradient learning.
method Generalizes neural tangent kernel (NTK) for surrogate gradient learning (SGL).
result Surrogate gradient NTK provides a good characterization of SGL.
SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustnesscs.LG
SAP corrects model for label noise by identifying and removing noisy samples.
problem Label corruption degrades model performance; acquiring perfect labels is costly.
method SAP uses SVD to identify and project model weights onto a clean activation space.
result SAP improves model generalization by up to 6% on CIFAR dataset with 25% synthetic corruption.
The choice of activation function can significantly influence the performance of neural networks. The lack of guiding principles for the selection of activation function is lamentable. We try to address this issue by introducing our variational neural networks, where the activation function is represented as a linear c…
A fast method for Lasso and Logistic Lasso problems.
problem Solving Lasso and Logistic Lasso regression problems efficiently.
method Iterative active set approach using solver updates.
result 31.41 times faster on average for compressed sensing.
Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only). Gating mechanisms that use softly saturating activation functions t…
New method trains neural networks with threshold activation functions efficiently.
problem Training neural networks with threshold activation functions is challenging due to zero gradients.
method We study weight decay regularized training problems of deep neural networks with threshold activations, showing they can be formulated as convex optimization problems.
result Regularized deep threshold network training problems can be formulated as standard convex optimization problems, paralleling the LASSO method.
The paper explores properties of projections and gradient methods in hyperbolic space forms.
problem Optimization problems in hyperbolic space forms.
method Intrinsic κ-projection and gradient projection methods.
result Every accumulation point of the sequence generated by the gradient projection method is a stationary point.
Geometric theory of projection heads in self-supervised learning.
problem Dimensional collapse and information invariance trade-off in projection heads.
method Geometric modeling of projection heads as Riemannian metrics, analyzing Hessian eigenvalues, and tracking optimization geometry.
result Smooth nonlinear heads induce negative curvature, preventing collapse; linear and ReLU heads cannot.
A new neural network layer integrates graph learning into classification tasks.
problem Lack of relational information in standard deep learning architectures for label predictions.
method Derives backpropagation equations for a differentiable graph learning layer.
result Smooth label transitions, improved generalization, and robustness to adversarial attacks.
We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of points that are disparate and high-magnitude when represented in a hallucinated gradient space, a strategy designed to incorporate both pred…
Optimizes reinsurance and investment strategies to minimize ruin probability.
problem Optimizing reinsurance and investment strategies to minimize ruin probability.
method Stochastic projected gradient method based on Malliavin calculus.
result Effectiveness of the proposed method demonstrated through numerical experiments.
Spectral gradient methods outperform Euclidean in certain deep learning scenarios.
problem When do spectral gradient updates outperform Euclidean in deep learning?
method Layerwise condition comparing squared nuclear-to-Frobenius ratio to stable rank of activations.
result Spectral updates can be more effective than Euclidean in deep networks and transformers.
In training speech recognition systems, labeling audio clips can be expensive, and not all data is equally valuable. Active learning aims to label only the most informative samples to reduce cost. For speech recognition, confidence scores and other likelihood-based active learning methods have been shown to be effectiv…
Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the memory cells mean an LSTM layer has four times as many parameters as an RNN with the…
Sketching algorithm finds closest point on convex hull efficiently.
problem Finding the closest point on a convex hull of large datasets.
method Sketching procedure to exploit data structure, gradient project method.
result Faster solution than standard optimization algorithms.
Paper proposes HTAF for stable training of binary neural networks.
problem Challenges in training binary neural networks with gradient-based optimization.
method HTAF is a smooth approximation to the Heaviside function that enables stable training.
result HTAF enables stable training of various binary neural networks with gradient-based optimization.
The goal of a recommendation system is to predict the interest of a user in a given item by exploiting the existing set of ratings as well as certain user/item features. A standard approach to modeling this problem is Inductive Matrix Completion where the predicted rating is modeled as an inner product of the user and …
Pre-conditioning is a well-known concept that can significantly improve the convergence of optimization algorithms. For noise-free problems, where good pre-conditioners are not known a priori, iterative linear algebra methods offer one way to efficiently construct them. For the stochastic optimization problems that dom…
LCW reduces activation shift in neural networks, improving training efficiency and generalization.
problem Activation shift in neural networks leading to non-zero mean preactivation values.
method Linearly constrained weights (LCW) to reduce activation shift in fully connected and convolutional layers.
result LCW resolves the vanishing gradient problem and improves generalization of neural networks.
We propose a novel Shapley value approach to help address neural networks' interpretability and "vanishing gradient" problems. Our method is based on an accurate analytical approximation to the Shapley value of a neuron with ReLU activation. This analytical approximation admits a linear propagation of relevance across …
New activation function BrownianReLU improves LSTM network performance on financial time series.
problem Gradient instability in noisy financial time series data.
method Introduces BrownianReLU, a stochastic activation function based on Brownian motion.
result Significantly improved predictive accuracy and generalization on financial datasets.
Wide networks with polynomial activations have proven asymptotic behavior.
problem Understanding the behavior of neural networks in the large width limit.
method Proving a conjecture for deep networks with polynomial activation functions.
result Tight bounds on the behavior of wide networks during stochastic gradient descent and derivation of their finite-width dynamics.
Paper introduces S3W distance for spherical probability distributions.
problem Comparing spherical probability distributions efficiently and accurately.
method S3W distance using stereographic projection and generalized Radon transform.
result Extensive theoretical analysis and evaluation of S3W performance.
We propose a new optimization method for training feed-forward neural networks. By rewriting the activation function as an equivalent proximal operator, we approximate a feed-forward neural network by adding the proximal operators to the objective function as penalties, hence we call the lifted proximal operator machin…
Ask-n-Learn uses gradient embeddings for active learning in image classification.
problem Efficiently labeling large amounts of training data for deep models.
method Gradient embeddings based on pseudo-labels, prediction calibration, and data augmentation.
result Significant improvements over state-of-the-art baselines on image classification tasks.
Gradient descent memorizes many Gaussians efficiently.
problem Memorizing many Gaussians with minimal parameters.
method Gradient descent on a depth-two neural network.
result One step of gradient descent memorizes $Ω\left(\frac{dq}{\log^4(d)}
ight)$ Gaussians.
Sparsification is an efficient approach to accelerate CNN inference, but it is challenging to take advantage of sparsity in training procedure because the involved gradients are dynamically changed. Actually, an important observation shows that most of the activation gradients in back-propagation are very close to zero…
We propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The local adaptation of activation function is achieved by introducing a scalable parameter in each lay…
Paper proposes a new method for efficient Pareto Front modeling.
problem Efficient modeling of Pareto Front (PF) in decision making problems.
method Projection based active Gaussian process regression (P-aGPR) method.
result The proposed method can provide a generative PF model and examine new points efficiently.
New flaw found in SAP defense, reducing its effectiveness to 0.1%.
problem Weakness in Stochastic Activation Pruning defense against adversarial attacks.
method Re-examined the implementation of SAP and introduced a new BPDA attack.
result SAP's effectiveness reduced to 0.1% when properly applied.