Revisits fuzzy neural networks with generalized Hamming distance, simplifying BN and ReLU.
problem Improving neural network techniques using fuzzy logic and generalized Hamming distance.
method Introducing generalized Hamming distance to reinterpret BN and ReLU, proposing GHN.
result Batch normalization and ReLU can be simplified or removed without loss of performance.
New STH distance finds patterns in event timeseries without resampling.
problem Lack of efficient analysis methods for event and state timeseries.
method Define STE-ts, propose STH, leveraging both time and state duration.
result Improved precision and computation time compared to resampled metrics.
ExDAG solves DAG learning problems with low structural Hamming distance.
problem Learning DAGs with low structural Hamming distance under identifiability assumptions.
method Mixed-integer quadratic programming (MIQP) with branch-and-bound-and-cut algorithm and lazy constraints.
result ExDAG guarantees global convergence and provides a real-time quality assessment.
Simple framework explains adversarial examples with small changes.
problem Understanding the ease of switching between decisions in targeted attacks.
method Developed a mathematical framework based on the geometry of L0 (Hamming) metric. result Quantitatively analyzed the number of input coordinates to change for misdirection.
Study shows effective resistance distance yields more accurate network barycenter than Hamming distance.
problem Identifying the best metric for computing the Fréchet mean network.
method Compared the effectiveness of Hamming distance and effective resistance distance in capturing network topology.
result Effective resistance distance produces a more accurate Fréchet mean network.
Differentially private data structures for estimating distances between strings.
problem Estimating distances between query strings and database strings while ensuring privacy.
method Proposes differentially private data structures for Hamming and edit distances using randomized response technique.
result Efficient data structures that provide accurate distance estimates with strong privacy guarantees.
Study robust mean estimation under coordinate-level corruptions using Hamming distance.
problem Robust mean estimation under realistic coordinate-level corruptions.
method Introduce a novel Hamming distance-based measure and present information-theoretic analysis.
result Data cleaning-inspired approaches can match information theoretic bounds for robust mean estimation.
New loss function and training scheme improve binary hash codes for better similarity search.
problem Improving binary hash codes for better similarity search tasks.
method Log likelihood loss on Hamming distance target, novel training scheme, multi-indexing.
result Significant improvements in MAP (84%) and query cost reduction for ImageNet and SIFT 1M.
Paper develops malware detection methods using Hamming distance.
problem Detecting and preventing spread of Android malware.
method Four detection methods using Hamming distance for similarity.
result Accuracy rates of proposed algorithms are more than 90%.
Asynchronous Gibbs sampling can accurately estimate expectations of functions of all variables under certain conditions.
problem Estimating expectations of functions of all variables in graphical models.
method Coupling synchronous and asynchronous Gibbs samplers to control expected Hamming distance, using concentration of measure results.
result The bias in estimating expectations of polynomial functions is smaller than the standard deviation of the function value in the true model.
Classifies homeomorphism groups of countable Stone spaces up to coarse equivalence.
problem Classifying non-locally compact topological groups using geometric group theory.
method Classification based on coarsely bounded sets and quasi-isometry.
result Groups in the second class are quasi-isometric to the Hamming cube.
New method identifies extreme risk propagation in financial networks.
problem Understanding extreme risk in financial networks.
method Max-linear structural equation model, hard-thresholding, Hamming distance.
result Sparse DAG for extreme risk propagation estimated.
New metric space for ReLU codes connects to network safety and robustness.
problem Lack of metrics capturing network safety and robustness beyond accuracy.
method Introduces a metric space of ReLU activation codes with a truncated Hamming distance.
result Establishes an isometry between ReLU codes and polyhedral bodies related to safety and robustness.
A new algorithm improves solving QAP with better performance.
problem Solving the Quadratic Assignment Problem (QAP) efficiently.
method Estimation of Distribution Algorithms (EDAs) with a non-parametric distance-based Mallows model.
result The proposed algorithm outperforms existing methods for QAP.
FSL-BM improves real-time classification with fuzzy logic and binary meta-features.
problem Real-time classification accuracy, memory consumption, and time complexity.
method FSL-BM integrates fuzzy logic, binary meta-features, Hamming Distance, and Hash function for efficient supervised learning.
result FSL-BM provides faster and more accurate real-time classification compared to existing algorithms.
A new, efficient k-modes algorithm improves clustering of categorical data.
problem Clustering categorical data using existing methods like k-means is inefficient. method Developed a novel k-modes algorithm called OTQT, which improves on existing methods. result OTQT finds more accurate clusters per iteration and is faster overall.
MUTE improves neural network performance with efficient target encoding.
problem Improving neural network performance with limited resources.
method MUTE optimizes Hamming distances among target encoding by understanding class confusion.
result MUTE offers better generalization and robustness with minimal overhead.
Large scale agglomerative clustering is hindered by computational burdens. We propose a novel scheme where exact inter-instance distance calculation is replaced by the Hamming distance between Kernelized Locality-Sensitive Hashing (KLSH) hashed values. This results in a method that drastically decreases computation tim…
Sharp threshold found for Frechet mean of inhomogeneous graphs.
problem Finding the Frechet mean of inhomogeneous Erdos-Renyi random graphs.
method Thresholding the expected adjacency matrix of the ensemble.
result The Frechet mean graph of inhomogeneous Erdos-Renyi random graphs exhibits a sharp threshold.
We extend the definition of Weinstein's Action homomorphism to Hamiltonian actions with equivariant moment maps of (possibly infinite-dimensional) Lie groups on symplectic manifolds, and show that under conditions including a uniform bound on the symplectic areas of geodesic triangles the resulting homomorphism extends…
Our work proves robustness of embedding schemes to discrete changes in text.
problem Discrete changes in text, like replacing a word, affect model robustness.
method Formal proofs and quantitative bounds for embedding schemes (concatenation, TF-IDF, Paragraph Vector).
result Embedding schemes are robust to discrete changes in text with Hölder or Lipschitz properties.
Hashing, or learning binary embeddings of data, is frequently used in nearest neighbor retrieval. In this paper, we develop learning to rank formulations for hashing, aimed at directly optimizing ranking-based evaluation metrics such as Average Precision (AP) and Normalized Discounted Cumulative Gain (NDCG). We first o…
Locality-sensitive hashing converts high-dimensional feature vectors, such as image and speech, into bit arrays and allows high-speed similarity calculation with the Hamming distance. There is a hashing scheme that maps feature vectors to bit arrays depending on the signs of the inner products between feature vectors a…
ECNN combines binary classifiers to protect neural networks from adversarial attacks.
problem Vulnerability of neural networks to adversarial inputs.
method Designs an error-correcting code matrix to maximize row and column distances, training end-to-end.
result ECNN effectively defends against adversarial attacks with good accuracy on normal examples.
New metrics improve learning of Gaussian networks.
problem Lack of suitable metrics for continuous Bayesian network learning.
method Introduce three-part minimum description length and renormalized normalized maximum likelihood metrics.
result Proposed metrics outperform BIC/AIC metrics in accuracy and convergence.
We prove that π1(Ham(M)) contains an infinite cyclic subgroup, where Ham(M) is the Hamiltonian group of the one point blow up of CP3. We give a sufficient condition for the group π1(Ham(M)) to contain an infinite cyclic subgroup, when M is a general toric manifold.
Let S(s,w) be the graph whose vertices are all subexpressions with target w of a fixed expression s in generators of a Coxeter group and edges are the pairs of subexpressions with Hamming distance 2. We prove that S(s,w) is connected and its cycle space …
Note proves bi-Lipschitz embeddings for Ham(S^2) metrics.
problem Entropy norms on Ham(S^2) bi-Lipschitz embeddings.
method Proves bi-Lipschitz embeddings for Ham(S^2) with entropy metrics.
result Existence of bi-Lipschitz embeddings for Ham(S^2) metrics.
A new metric compares true and learned causal graphs considering data and graph structure.
problem Comparing true and learned causal graphs accurately.
method Continuous Structural Intervention Distance (CSID) using conditional mean embeddings and maximum mean discrepancy.
result Validated the CSID with synthetic data, showing its effectiveness in comparing causal graphs.
Causal inference relies on the structure of a graph, often a directed acyclic graph (DAG). Different graphs may result in different causal inference statements and different intervention distributions. To quantify such differences, we propose a (pre-) distance between DAGs, the structural intervention distance (SID). T…
The paper constructs quasimorphisms on surface diffeomorphism groups with entropy bounds.
problem Entropy bounds on surface diffeomorphism groups.
method Constructing homogeneous quasimorphisms and defining entropy metrics.
result There are infinitely many linearly independent quasimorphisms with entropy bounds.
New measures assess differences in causal graphs' separations.
problem Evaluating causal discovery algorithms' output.
method Proposes new distance measures capturing causal graphs' separations.
result Proposed distances assess differences in causal graphs' separations.
A new matching method for causal inference that handles irrelevant variables and missing data.
problem Creating high-quality treatment-control matches for categorical data in social sciences.
method A weighted Hamming distance matching method that considers covariate importance and creates a hierarchy of covariate combinations.
result The method produces high-quality matches and handles irrelevant variables and missing data.
NESTA accelerates neural networks by compressing Hamming weights.
problem Efficiently computing convolution layers in deep neural networks.
method NESTA reformats convolutions into 3imes3 batches and uses Hamming Weight Compressors to process each batch, approximating partial sums and adding residuals. result Significantly speeds up convolution computations with reduced energy consumption.
PAIR-CI calibrates CI tests for causal discovery with incomplete data.
problem Miscalibration of CI tests when imputing incomplete data.
method Integrates multiple imputation directly into the inferential procedure via a paired permutation design.
result PAIR-CI reduces false positive rates to below 5% in simulations.
We verify here some variants of topological and dynamical flavor of the injectivity radius conjecture in Hofer geometry, Lalonde-Savelyev \cite{citeLalondeSavelyevOntheinjectivityradiusinHofergeometry} in the case of Ham(S2) and Ham(Σ,ω), for Σ a closed positive genus surface. In particular we show that any lo…
New neural network outperforms existing methods in scene matching.
problem Automated scene matching with high accuracy and low false positives.
method Convolutional hashing using a new loss function and training scheme.
result Significantly higher true positive rate and 100-fold reduction in false positives.
This paper compares FAISS and FENSHSES for nearest neighbor search in Hamming space.
problem Comparing nearest neighbor search systems in Hamming space.
method Comprehensive evaluations of indexing speed, search latency, and RAM consumption.
result Better understanding of trade-offs between main memory and secondary memory systems.
Multi-label classification is a type of supervised learning where an instance may belong to multiple labels simultaneously. Predicting each label independently has been criticized for not exploiting any correlation between labels. In this paper we propose a novel approach, Nearest Labelset using Double Distances (NLDD)…
Proposes a new Bayesian score for learning network structure from related datasets.
problem Learning network structure from heterogeneous related data sets.
method Bayesian Hierarchical Dirichlet (BHD) score based on a hierarchical model.
result BHD outperforms BDeu in reconstruction accuracy and sparsity for related datasets.
Develops homotopies for Lagrangian field theory using advanced algebraic structures.
problem Formulating a consistent framework for Lagrangian field theory.
method Introduces L∞ algebras and homotopies to enrich the Batalin-Vilkovisky framework. result Provides an explicit lift of the Batalin-Vilkovisky framework to local forms.
Paper presents a new trie for integer sketches to improve similarity searches.
problem Efficient similarity searches on integer sketches.
method Introduces a novel b-bit sketch trie that leverages succinct data structures. result Significantly improves search time and space-efficiency of similarity searches.
Lower bound found for fragmentation norm, embedding provided.
problem Fragmentation norms on Hamiltonian diffeomorphisms of surfaces.
method Lower bound calculation and bi-Lipschitz embedding construction.
result Lower bound for fragmentation norm and embedding provided.
We introduce here a natural functional associated to any b∈QH∗(M,ω): \emph{spectral length functional}, on the space of "generalized paths" in Ham(M,ω), closely related to both the Hofer length functional and spectral invariants and establish some of its properties. This functional is smooth on its…
Consider a linear regression model where the design matrix X has n rows and p columns. We assume (a) p is much large than n, (b) the coefficient vector beta is sparse in the sense that only a small fraction of its coordinates is nonzero, and (c) the Gram matrix G = X'X is sparse in the sense that each row has relativel…
We apply Gromov's ham sandwich method to get (1) domain monotonicity (up to a multiplicative constant factor); (2) reverse domain monotonicity (up to a multiplicative constant factor); and (3) universal inequalities for Neumann eigenvalues of the Laplacian on bounded convex domains in a Euclidean space.
The paper proposes a semi-parametric Bayesian network model using Gaussian Processes and Horseshoe priors.
problem Learning semi-parametric relationships in Expert Bayesian Networks with minimal nonlinear components.
method Uses Gaussian Processes and Horseshoe priors to model relationships, prioritizes modifying expert graphs, and generates diverse graphs.
result Models outperform state-of-the-art semi-parametric Bayesian Network models in synthetic and real-world datasets.
Let Σ_g be a closed orientable surface let Diff_0(Σ_g; area) be the identity component of the group of area-preserving diffeomorphisms of Σ_g. In this work we present an extension of Gambaudo-Ghys construction to the case of a closed hyperbolic surface Σ_g, i.e. we show that every non-trivial homogeneous quasi-morphism…