Generative model attacks CNN on MNIST by subtly replacing input patterns.
problem Adversarial attacks on neural networks.
method Generative model that replaces input patterns with generated ones.
result Demonstrated effectiveness on MNIST dataset.
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 “pattern replacement”
Parrot learns optimal cache replacement policies using imitation learning.
problem Improving cache hit rates in complex access patterns.
method Imitation learning approach using Belady's oracle policy.
result Parrot increases cache hit rates by 61% on a web search benchmark.
WTM reduces clause usage and computation time for pattern recognition.
problem High computation time and memory usage in Tsetlin Machine.
method Weighting clauses and using binomial sampling to reduce complexity.
result WTM achieves similar accuracy with fewer clauses and faster training.
Self-attention can replace convolutional layers in vision tasks.
problem The supremacy of convolutional layers in vision tasks.
method Analysis and experiments with self-attention layers compared to convolutional layers.
result Self-attention layers can perform as well as convolutional layers and learn to do so.
The explosion in workload complexity and the recent slow-down in Moore's law scaling call for new approaches towards efficient computing. Researchers are now beginning to use recent advances in machine learning in software optimizations, augmenting or replacing traditional heuristics and data structures. However, the s…
General Vector Machinestat.ML
The support vector machine (SVM) is an important class of learning machines for function approach, pattern recognition, and time-serious prediction, etc. It maps samples into the feature space by so-called support vectors of selected samples, and then feature vectors are separated by maximum margin hyperplane. The pres…
Survey on discrete minimal surfaces and their properties.
problem Discretizing minimal surfaces in Euclidean space.
method Polyhedral surfaces with parallel face offsets and circle patterns.
result All simply connected discrete minimal surfaces can be constructed from circle patterns.
Formula removes geometric patterns from random hyperbolic surfaces.
problem Conditioning on tangle-free surfaces to avoid rare geometric patterns.
method Developed a Moebius inversion formula to integrate tangle-free surfaces.
result Significantly reduces the number of local topological types of short geodesics.
Boolean matrix factorization (BMF) is a popular and powerful technique for inferring knowledge from data. The mining result is the Boolean product of two matrices, approximating the input dataset. The Boolean product is a disjunction of rank-1 binary matrices, each describing a feature-relation, called pattern, for a g…
Machine Learning (ML) helps us to recognize patterns from raw data. ML is used in numerous domains i.e. biomedical, agricultural, food technology, etc. Despite recent technological advancements, there is still room for substantial improvement in prediction. Current ML models are based on classical theories of probabili…
This is an up-to-date introduction to and overview of the Minimum Description Length (MDL) Principle, a theory of inductive inference that can be applied to general problems in statistics, machine learning and pattern recognition. While MDL was originally based on data compression ideas, this introduction can be read w…
A good cover in R^d is a collection of open contractible sets in R^d such that the intersection of any subcollection is either contractible or empty. Motivated by an analogy with convex sets, intersection patterns of good covers were studied intensively. Our main result is that intersection patterns of good covers are …
The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it can be hardly used in the training phase because the training phase involves dense matrix-multiplicatio…
Diffusion Representationsstat.ML
Diffusion Maps framework is a kernel based method for manifold learning and data analysis that defines diffusion similarities by imposing a Markovian process on the given dataset. Analysis by this process uncovers the intrinsic geometric structures in the data. Recently, it was suggested to replace the standard kernel …
The Epochal Sawtooth Phenomenon: Unveiling Training Loss Oscillations in Adam and Other Optimizerscs.LG
This paper identifies and analyzes the Epochal Sawtooth Phenomenon in training loss curves.
problem Training loss oscillations in adaptive gradient-based optimizers.
method Empirical analysis of Adam and other optimizers, focusing on parameters, batch size, data shuffling, and sample replacement.
result The Epochal Sawtooth Phenomenon (ESP) is a recurring pattern in training loss curves, arising from adaptive learning rate adjustments and data shuffling.
Machine Learning has become very famous currently which assist in identifying the patterns from the raw data. Technological advancement has led to substantial improvement in Machine Learning which, thus helping to improve prediction. Current Machine Learning models are based on Classical Theory, which can be replaced b…
This paper finds a new way to compress CNN weights, improving on pruning and quantization.
problem Improving performance and storage efficiency of CNNs.
method Identifying and exploiting repeated patterns in CNN weight tensors, using Huffman coding and block sparse matrix formats.
result Achieved compaction ratios of 1.4x to 3.1x in addition to pruning and quantization.
GGP models multivariate time series with latent sub-sequences for diverse behaviors.
problem Modeling multivariate time series with diverse behaviors and patterns.
method Graph Gamma Process (GGP) linear dynamical systems with latent sub-sequences.
result GGP models exhibit good predictive performance and reveal interpretable latent patterns.
Enhances GNNs to better capture local graph structures.
problem Limited expressiveness of GNNs due to star-shaped message passing.
method Extends local aggregation to subgraph patterns using GNN encoders.
result Significantly improved performance on graph ML tasks.
Improved CTR prediction with XDBoost neural network.
problem Predicting CTR with limited data and complex user behavior.
method Iterative three-stage neural network model XDBoost.
result XDBoost outperforms existing SOTA models for CTR prediction.
Efficient Convolutional Network Learning using Parametric Log based Dual-Tree Wavelet ScatterNetcs.LG
We propose a DTCWT ScatterNet Convolutional Neural Network (DTSCNN) formed by replacing the first few layers of a CNN network with a parametric log based DTCWT ScatterNet. The ScatterNet extracts edge based invariant representations that are used by the later layers of the CNN to learn high-level features. This improve…
Standard kernels such as Matérn or RBF kernels only encode simple monotonic dependencies within the input space. Spectral mixture kernels have been proposed as general-purpose, flexible kernels for learning and discovering more complicated patterns in the data. Spectral mixture kernels have recently been generalized in…
Matroid Regressionmath.ST
We propose an algebraic combinatorial method for solving large sparse linear systems of equations locally - that is, a method which can compute single evaluations of the signal without computing the whole signal. The method scales only in the sparsity of the system and not in its size, and allows to provide error estim…
Spatial graphs study tangle replacement with equivalence classes.
problem Differentiating spatial graphs and their properties.
method Tangle replacement on spatial graphs, focusing on handcuff graphs.
result One-to-one correspondence between neighborhood equivalence classes and tangles.
Improved molecular property prediction using WL embedding in GNNs.
problem Limited performance of GNNs in predicting molecular properties.
method Explored Weisfeiler-Lehman (WL) embedding to replace GNN layers, enhancing representability and performance.
result WL embedding consistently improves GNN performance across multiple datasets.
We introduce new symplectic cut-and-paste operations that generalize the rational blowdown. In particular, we will define -replaceable plumbings to be those that, heuristically, can be symplectically replaced by Euler characteristic 4-manifolds. We will then classify 2-replaceable linear plumbings, construct 2-r…
Study shows Heegaard genus relation in 3-manifold amalgamation.
problem Understanding Heegaard genus in 3-manifold amalgamation.
method Examined amalgamation of 3-manifolds, used degree-one maps, and fixed boundary conditions.
result Proved , showing Heegaard genus relation.
Efficiently samples sequences without replacement for machine learning models.
problem Generating diverse outputs from sequential models without duplicates.
method Incremental sampling procedure for randomized programs, including neural models.
result Efficacy and flexibility of incremental sampling for large output spaces.
Research on predicting with lists of labels, characterizing learnability and providing algorithms.
problem Multiclass online prediction with multiple labels.
method Characterization using -ary Littlestone dimension, adaptation of classical algorithms, combinatorial results.
result Achievement of negative regret in some scenarios, complete characterization of learnability.
This paper addresses credit valuation adjustment with a new closeout convention.
problem Accurate estimation of financial claim value considering counterparty credit risk.
method Theoretical and computational analysis of a nonlinear valuation system using neural networks.
result A neural network-based algorithm effectively solves the high-dimensional nonlinear valuation system.
SGD without replacement decouples into curvature-following and flatness-regularizing steps.
problem Theoretical analysis of SGD without replacement for large-scale neural networks.
method Analysis of SGD without replacement in a realistic regime, considering high curvature and flatness.
result Optimizing with SGD without replacement is locally equivalent to an additional regularizer step.
Develops algorithms to optimize machine replacement schedules using operational data.
problem Optimizing machine replacement intervals when the lifetime distribution is unknown.
method Formulates as a stochastic multi-armed bandit problem and proposes Hoeffding- and Bernstein-based algorithms.
result Achieves optimal or near-optimal replacement intervals with minimal regret.
Event-based models (EBM) are a class of disease progression models that can be used to estimate temporal ordering of neuropathological changes from cross-sectional data. Current EBMs only handle scalar biomarkers, such as regional volumes, as inputs. However, regional aggregates are a crude summary of the underlying hi…
Tangle replacements help in understanding knot properties.
problem Understanding the minimum number of tangle replacements to unknot a knot.
method Using knot Floer homology torsion to find lower bounds.
result Torsion order gives a lower bound on the minimum number of tangle replacements.
Paper closes convergence gap for SGD without replacement.
problem Establishing convergence rate for SGD without replacement.
method Analyzes convergence rates for strongly convex and smooth functions.
result Achieves a rate of O(1/T^2 + n^2/T^3) for quadratic sums.
Improved GAN performance with a novel local attention mechanism.
problem Enhancing the performance of Generative Adversarial Networks (GANs).
method Introducing a two-dimensional local attention mechanism that preserves geometry and locality, and using information flow graphs for design.
result Significant improvements in FID and Inception scores, from 18.65 to 15.94 on ImageNet.
New method for simplifying knots with specific properties.
problem Understanding knots with a specific unknotting number.
method Derive and apply the Montesinos trick for proper rational tangle replacement.
result Prove that knots with proper rational unknotting number one are prime and classify certain types.
Safe Pattern Pruning reduces pattern explosion in predictive pattern mining.
problem Exponential growth of patterns in structured data.
method Safe Pattern Pruning (SPP) method.
result Effective model building in practical data analysis.
MPTE uses Transformer attention to estimate mixed-frequency factor models.
problem Estimating factor models in panel datasets with mixed frequencies and nonlinear signals.
method Mixed-Panels-Transformer Encoder (MPTE) with attention mechanisms.
result MPTE achieves competitive performance in nonlinear forecasting environments.
If M and N are equivariantly homotopy equivalent G-manifolds, then the fixed sets M^G and N^G are also homotopy equivalent. The replacement problem asks the converse question: If F is homotopy equivalent to the fixed set M^G, is F = N^G for a G-manifold equivariantly homotopy equivalent to M? We prove that for locally …
Proposes a model for predicting events from event streams.
problem Predicting events like part replacement and failure in manufacturing and teleservice systems.
method Non-parametric prognostic framework using MGCP modulated Poisson processes.
result MGCP prior facilitates sharing of information and analysis of flexible event patterns.
Sampling without replacement speeds up optimization in minimax problems.
problem Optimizing minimax problems with faster convergence rates.
method Analysis of gradient descent ascent and proximal point method with two sampling strategies.
result Sampling without replacement leads to faster convergence rates in minimax optimization.
Hebbian-Descentcs.LG
In this work we propose Hebbian-descent as a biologically plausible learning rule for hetero-associative as well as auto-associative learning in single layer artificial neural networks. It can be used as a replacement for gradient descent as well as Hebbian learning, in particular in online learning, as it inherits the…
BN^2MF identifies unknown exposure patterns in environmental mixtures.
problem Identifying unknown exposure patterns in environmental mixtures.
method Bayesian non-parametric non-negative matrix factorization (BN^2MF) with non-negative continuous priors and a non-parametric sparse prior.
result Estimates patterns of chemical exposures without specifying the number of patterns.
New research disproves a key conjecture in optimization.
problem Comparison of sampling methods in stochastic optimization.
method Reduction to noncommutative arithmetic-geometric mean inequality and application of noncommutative Positivstellensatz.
result The Recht-Ré conjecture is false for general n.
RestoreAI predicts landmine risk from patterns, improving clearance efficiency.
problem Predicting landmine risk from spatial patterns to enhance clearance efficiency.
method RestoreAI uses landmine patterns for risk prediction, implementing three deminers: linear, curved, and Bayesian.
result RestoreAI significantly boosts clearance efficiency, achieving a 14.37 percentage point increase in cleared landmines per timestep.
The paper explores MAB strategies for very short horizons, introducing new methods and showing improved performance.
problem Short horizon multi-armed bandit problems in games.
method Regression oracles, forced exploration, UCBT strategy.
result Combination of epsilon-greedy or epsilon-decreasing with regression oracles outperforms other strategies.
Study of knots with generalized Mazur patterns and their invariants.
problem Understanding the invariants and properties of knots with generalized Mazur patterns.
method Computational analysis of and invariants for -twisted satellites.
result None of the -twisted patterns from the family act surjectively on the smooth or rational concordance group.