New inequality for odd-degree flexible curves using surface doubling.
problem Bounding the number of non-empty ovals of odd-degree flexible curves.
method Defining an Arnold surface for odd-degree flexible curves and using it to derive a Viro--Zvonilov-type inequality.
result Upper bound on the number of non-empty ovals of odd-degree flexible curves.
Proposes neural similarity for CNNs to enhance flexibility and performance.
problem Limited flexibility of inner product-based convolution in CNNs.
method Introduces neural similarity as a learnable parametric similarity measure, and proposes NSL for adaptive learning from data.
result Dynamic neural similarity improves flexibility and performance in visual recognition and few-shot learning.
This paper proposes Relational Similarity Machines (RSM): a fast, accurate, and flexible relational learning framework for supervised and semi-supervised learning tasks. Despite the importance of relational learning, most existing methods are hard to adapt to different settings, due to issues with efficiency, scalabili…
CEBMs learn flexible latent mappings from data.
problem Learning flexible latent mappings from data.
method CEBMs decompose joint density into tractable posterior over latent variables.
result CEBMs achieve competitive results in image modeling and latent space predictive power.
A new hashing method handles large-scale data with flexible similarity measures.
problem Efficient nearest neighbour search in large-scale systems with variable labels.
method End-to-end trainable network transforming data to uniform distribution on product of spheres, then hashing to binary form maximizing entropy.
result Outperforms baseline approaches in limited capacity regime.
Unsupervised two-view learning, or detection of dependencies between two paired data sets, is typically done by some variant of canonical correlation analysis (CCA). CCA searches for a linear projection for each view, such that the correlations between the projections are maximized. The solution is invariant to any lin…
Limbo is an open-source C++11 library for Bayesian optimization which is designed to be both highly flexible and very fast. It can be used to optimize functions for which the gradient is unknown, evaluations are expensive, and runtime cost matters (e.g., on embedded systems or robots). Benchmarks on standard functions …
Algorithm improves transfer learning by inferring successor maps.
problem Machine learning challenges in multi-task scenarios.
method Combining factorized representations and nonparametric memory-based approaches.
result Improves transfer capabilities and outperforms other algorithms.
We prove a triangulation theorem for semi-algebraic sets over a p-adically closed field, quite similar to its real counterpart. We derive from it several applications like the existence of flexible retractions and splitting for semi-algebraic sets.
Paper develops active learning for clustering unknown pairwise similarities.
problem Learning positive and negative pairwise similarities efficiently.
method Generic active learning framework for correlation clustering.
result Demonstrates effectiveness of query strategies in clustering.
Paper tackles weakly supervised learning from similarity-confidence data.
problem Learning binary classifier from unlabeled data pairs with confidence of similarity.
method Proposes an unbiased estimator of classification risk from Sconf data and risk correction scheme.
result Demonstrates effectiveness of proposed methods through experiments.
tsflex speeds up time series processing and feature extraction.
problem Inefficient and inflexible time series processing tools.
method Flexible Python toolkit exttttsflex for multivariate, asynchronous time series. result Significantly faster and more memory-efficient than existing packages.
Flexible log file parsing using HMM adapts to evolving content.
problem Dynamic log file processing with evolving content.
method Modeling frequent patterns into HMM for flexible log file parsing.
result High accuracy (over 99%) in parsing different system log files.
A general framework for solving the subspace clustering problem using the CUR decomposition is presented. The CUR decomposition provides a natural way to construct similarity matrices for data that come from a union of unknown subspaces U=i=1⋃MSi. The similarity matrices thus c…
Improved A/B testing by leveraging system similarities.
problem Traditional A/B testing ignores potential system similarities.
method Off-policy estimation to exploit system propensities.
result Improved A/B testing estimators achieve better accuracy.
PDSketch enables flexible robot planning by learning from domain structures.
problem Building general robots with flexible planning.
method Exploiting locality and sparsity in environmental models, PDSketch defines high-level structures for trainable neural networks.
result PDSketch automatically generates planning heuristics without additional training.
Graph neural networks improve with edge similarity constraints in RNA structure analysis.
problem Lack of edge similarity constraints in graph neural networks.
method Introduced a graph neural network layer that leverages prior information about edge similarities.
result Edge similarity constraints do not enhance performance in graph neural networks.
URN neural network dynamically generates various neural structures during training.
problem Creating neural networks with flexible, dynamic structures during training.
method Introduced Unstructured Recursive Network (URN) and used gradient descent on a single loss function.
result Different neural structures can emerge from a single URN during training.
Proposes rpf-kernel for clustering via random projection forests.
problem Clustering similar data points while distinguishing them from dissimilar ones.
method Random projection forests to learn a similarity kernel.
result rpf-kernel effectively clusters data with competitive performance.
RFA-LCF improves clustering accuracy by robustly handling noise and errors.
problem Inaccurate representation and clustering results due to noise and hard constraints.
method Integrates robust flexible CF, sparse local-coordinate coding, and adaptive weighting into a unified model.
result Delivers state-of-the-art clustering results on public databases.
Drug similarity has been studied to support downstream clinical tasks such as inferring novel properties of drugs (e.g. side effects, indications, interactions) from known properties. The growing availability of new types of drug features brings the opportunity of learning a more comprehensive and accurate drug similar…
SC-InfoNCE improves InfoNCE for feature clustering in contrastive learning.
problem Lack of theoretical understanding of InfoNCE's feature clustering mechanism.
method Introduced a transition probability matrix to model data augmentation dynamics and optimize feature similarity.
result SC-InfoNCE achieves strong performance across diverse domains, aligning feature similarity with downstream data.
The Pachinko Allocation Machine (PAM) is a deep topic model that allows representing rich correlation structures among topics by a directed acyclic graph over topics. Because of the flexibility of the model, however, approximate inference is very difficult. Perhaps for this reason, only a small number of potential PAM …
Flexible multi-task learning framework using summary statistics.
problem Data-sharing constraints in healthcare settings.
method Proposes a flexible multi-task learning framework utilizing summary statistics and adaptive parameter selection.
result Systematic non-asymptotic analysis and simulations demonstrate the method's performance.
Researchers develop flexible kernels for biological sequences with guaranteed reliability.
problem Challenges in applying machine learning to biological sequences, including unreliable methods.
method Theoretical analysis and development of modified kernels to ensure reliability and accuracy.
result Developed kernels that are universal, characteristic, and metrize the space of distributions for biological sequences.
Extends matrix factorization for deviance-based losses with GLM theory.
problem Improving data loss models beyond squared error.
method Adapts GLM theory to matrix factorization for deviance losses.
result Strong consistency and robustness of the proposed decomposition.
Algorithm learns similarity metrics for individual fairness.
problem Difficulty in learning similarity metrics for individual fairness.
method Gradient descent and Bradley-Terry model for pairwise comparisons.
result Algorithm converges to ground truth metric for individual fairness.
Interactive DR framework for comparing datasets.
problem Limited flexibility in existing DR methods for comparative analysis.
method Unified linear comparative analysis (ULCA) with interactive optimization and visualization.
result ULCA and optimization algorithm improve comparative analysis efficiency and flexibility.
Flexible nonstationary Gaussian process with neural network parameters.
problem Limited expressiveness of stationary Gaussian processes.
method Nonstationary kernels with neural network parameters trained jointly.
result Better accuracy and log-score compared to stationary and hierarchical models.
Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D d…
Paper tests similarity between networks using a bootstrap method.
problem Determining if two networks are similar or proportional.
method Parametric bootstrap approach and Frobenius norm-based test.
result The method is versatile and consistent under various models.
Partial fusion combines neural networks to balance accuracy and efficiency.
problem Balancing accuracy and computational cost in neural networks.
method Extending weight aggregation methods based on neuron-level similarity, using partial optimal transport to match similar neurons.
result Achieves a flexible tradeoff between computational cost and performance.
Active learning optimizes correlation clustering by querying the most informative pairwise comparisons.
problem Efficiently clustering data with limited pairwise similarity information.
method Developed principled active learning approach using information-theoretic acquisition functions.
result Significantly outperforms existing baselines in clustering accuracy and query efficiency.
New tractable density models from squaring neural networks.
problem Flexible models for probability distributions in machine learning.
method Squared Neural Family (SNEFY) models formed by squaring neural network outputs and normalizing.
result SNEFYs are fully tractable with closed form normalizing constants in many cases.
Enhances source domain knowledge with target data for transfer learning.
problem Limited data in target domains and rigid model assumptions in transfer learning.
method Transfer learning through Enhanced Sufficient Representation (TESR).
result TESR enhances source domain knowledge with target data, improving transfer learning performance.
We investigate task clustering for deep-learning based multi-task and few-shot learning in a many-task setting. We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario. Although this matrix provides us critical information regarding similarity betw…
BFPM improves machine learning accuracy by considering object types and memberships flexibly.
problem Inaccurate learning due to missing important parameters.
method BFPM relaxes fuzzy and possibilistic constraints, allowing arbitrary object memberships and movement analysis.
result BFPM enhances object movement analysis and provides flexible search space.
In many structured prediction problems, complex relationships between variables are compactly defined using graphical structures. The most prevalent graphical prediction methods---probabilistic graphical models and large margin methods---have their own distinct strengths but also possess significant drawbacks. Conditio…
Paper introduces kernel deformed exponential families for sparse continuous attention.
problem Creating efficient attention mechanisms for sparse data.
method Developed kernel deformed exponential families, theoretically and experimentally.
result Kernel deformed exponential families can attend to multiple compact regions of data.
Graph convolutional deep kernel machine learns representations for graph tasks.
problem Limited representation learning in infinite-width neural networks.
method Developed a graph convolutional deep kernel machine as an infinite-width limit.
result Representation learning improves performance for heterophilous node classification tasks.
Pyramid Attention Networks improve image restoration by leveraging self-similarities across scales.
problem Lack of full exploitation of self-similarities in image restoration by recent deep learning methods.
method Introduces a Pyramid Attention module that processes multi-scale feature correspondences to borrow clean signals from coarser levels.
result Pyramid Attention module achieves state-of-the-art results in various image restoration tasks.
Levy copulas are the most general concept to capture jump dependence in multivariate Levy processes. They translate the intuition and many features of the copula concept into a time series setting. A challenge faced by both, distributional and Levy copulas, is to find flexible but still applicable models for higher dim…
MoE-Sim-VAE clusters and generates data from similarity-based representations.
problem Clustering high-dimensional data like biological measurements.
method Variational Autoencoder with Mixture-of-Experts architecture.
result MoE-Sim-VAE outperforms other methods in clustering and generating realistic data.
We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label. We use a deep lattice network model so we can architect the model structure to enhance interpretability, and add monotonicity constraints between inputs-and-outputs.…
Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning technique…
A new density model using Fourier basis achieves better approximations and compression.
problem Approximating multi-modal 1D densities.
method Constrained Fourier basis model for end-to-end training.
result Lower cross entropy compared to deep factorized models.
We develop unbiased implicit variational inference (UIVI), a method that expands the applicability of variational inference by defining an expressive variational family. UIVI considers an implicit variational distribution obtained in a hierarchical manner using a simple reparameterizable distribution whose variational …
A folded type model is developed for analyzing compositional data. The proposed model involves an extension of the α-transformation for compositional data and provides a new and flexible class of distributions for modeling data defined on the simplex sample space. Despite its rather seemingly complex structure, emplo…