A new permutation method improves two-sample testing power.
problem Two-sample testing with improved power and validity.
method Structured block-restricted cross-swaps.
result Block-restricted permutations achieve higher power than full permutations.
PARD generates graphs efficiently and invariantly to node ordering.
problem Graph generation sensitivity to node ordering.
method Integrates autoregressive and diffusion models with a partial order for nodes and edges.
result PARD achieves state-of-the-art performance on molecular and non-molecular datasets.
We tackle tensor denoising with unknown permutations, achieving optimal recovery with polynomial estimators.
problem Structured tensor denoising with unknown permutations in recommendation systems, neuroimaging, etc.
method Developed a constrained least-squares estimator in a block-wise polynomial family.
result Achieved the minimax error bound with polynomial estimators of degree up to (m−2)(m+1)/2. SPAN learns functions over sets invariant to permutations, outperforming existing methods.
problem Learning functions over sets invariant to permutations.
method SPAN architecture that combines neural networks with adversarial permutations.
result SPAN achieves nearly permutation-invariant functions while maintaining accuracy.
New basis for permutation equivariant layers reduces computation costs.
problem Efficiently computing permutation equivariant layers in neural networks.
method Generalized partition algebra basis with low-rank tensors.
result Low-rank tensors enable faster computation compared to orbit basis.
Transformers tend to learn more symmetric functions in sequence data.
problem Understanding inductive bias in Transformers with infinitely over-parameterized models.
method Analyzing Transformers in the Gaussian process limit, using representation theory of the symmetric group.
result Transformers are biased towards more permutation symmetric functions, and this can be quantitatively predicted.
Entity resolution seeks to merge databases as to remove duplicate entries where unique identifiers are typically unknown. We review modern blocking approaches for entity resolution, focusing on those based upon locality sensitive hashing (LSH). First, we introduce k-means locality sensitive hashing (KLSH), which is b…
New method tests independence in time series data.
problem Testing independence between time series data.
method Temporal dependence statistic with block permutation.
result Asymptotically valid and universally consistent test for independence.
Synthetic augmentation improves financial machine learning performance in variance-dominant regimes.
problem Data scarcity in financial machine learning.
method Formalized synthetic augmentation, introduced size-matched null augmentation, and developed a non-parametric block permutation test.
result Synthetic augmentation is beneficial only in variance-dominant regimes, such as persistent volatility forecasting.
Spectral methods achieve near-optimal performance in orthogonal and permutation group synchronization.
problem Recovering group elements from pairwise measurements in computer vision.
method Spectral methods applied with the leave-one-out technique.
result Near-optimal performance bounds for orthogonal and permutation group synchronization established.
Positive permutation braids on n strings, which are defined to be positive n-braids where each pair of strings crosses at most once, form the elementary but non-trivial building blocks in many studies of conjugacy in the braid groups. We consider conjugacy among these elementary braids which close to knots, and show th…
The paper connects GL-racks to knot coloring invariants.
problem Understanding invariants of Legendrian knots.
method Exploring GL-racks and their decomposition into permutation and block GL-racks.
result Equivalent coloring invariants for knots with identical classical invariants.
Deep neural networks (DNNs) have become the state-of-the-art technique for machine learning tasks in various applications. However, due to their size and the computational complexity, large DNNs are not readily deployable on edge devices in real-time. To manage complexity and accelerate computation, network compression…
New method identifies latent variables with sparse perturbations.
problem Identifying latent variables with minimal supervision.
method Weakly supervised representation learning with sparse perturbations.
result Identification of latent variables up to specified blocks.
Hybrid diarization framework handles overlapped speech and long recordings.
problem Challenges in clustering-based and end-to-end neural diarization approaches.
method Proposes a hybrid framework combining clustering and end-to-end neural diarization.
result Significantly better performance on long recordings with overlapped speech.
HaKAN uses Hahn-KAN blocks to forecast multivariate time series.
problem Long-term time series forecasting challenges with high complexity and spectral bias.
method HaKAN integrates channel independence, patching, and a stack of Hahn-KAN blocks with residual connections. It uses Hahn polynomial-based learnable activation functions.
result HaKAN consistently outperforms state-of-the-art methods on various forecasting benchmarks.
Paper tightens sample complexity for Mallows and Generalized Mallows Models.
problem Estimating parameters of Mallows and Generalized Mallows Models.
method Introduced Mallows Block Model to analyze and derive tight sample complexity bounds.
result Tight sample complexity bound for learning Mallows and Generalized Mallows Model.
Graph Neural Networks struggle on random graphs without node identifiers.
problem Graph Neural Networks' limitations on random graphs without node identifiers.
method Study of Graph Neural Networks and Structural Graph Neural Networks convergence on large random graphs.
result Structural Graph Neural Networks are more powerful and universal than Graph Neural Networks on random graphs.
Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collectio…
New method for deep learning hierarchies like sequences and graphs.
problem Lack of formalism for dealing with hierarchical structures in deep learning.
method Express equivariant maps for hierarchies using combinations of building block symmetries.
result Demonstrates effectiveness on semantic segmentation of point-cloud data.
We extend conformal inference to general settings that allow for time series data. Our proposal is developed as a randomization method and accounts for potential serial dependence by including block structures in the permutation scheme. As a result, the proposed method retains the exact, model-free validity when the da…
This paper tackles fitting multilevel low rank matrices by addressing three problems.
problem Fitting a given matrix by an MLR matrix in the Frobenius norm.
method Factor fitting, rank allocation, and hierarchical partitioning.
result The proposed methods can fit a given matrix by an MLR matrix in the Frobenius norm.
New neural network learns set-equivariant functions efficiently.
problem Efficiently implementing and learning set-equivariant functions.
method Gated recurrent network applied iteratively to all entities and syncs with population progression.
result SWARM mappings achieve state-of-the-art performance in various applications.
New fusion blocks improve equivariant neural networks for molecular dynamics.
problem Designing equivariant neural networks for tasks with global symmetries.
method Using fusion diagrams from tensor networks to design novel equivariant components.
result Improved performance with fewer parameters on chemical problems.
Cryptocurrency markets show similar returns but different volatility responses to infrastructure and regulatory shocks.
problem Understanding how cryptocurrency markets differentiate between infrastructure and regulatory shocks.
method Event-level block bootstrap inference on 31 cryptocurrency events across Bitcoin, Ethereum, Solana, and Cardano (2019-2025).
result No statistically significant difference in cumulative abnormal returns between infrastructure failures and regulatory enforcement.
Motivated by large-scale Collaborative-Filtering applications, we present a Non-Commuting Latent Factor (NCLF) tensor-completion approach for modeling three-way arrays, which is diagonal like the standard PARAFAC, but wherein different terms distinguish different kinds of three-way relations of co-clusters, as determin…
We introduce the Kronecker factored online Laplace approximation for overcoming catastrophic forgetting in neural networks. The method is grounded in a Bayesian online learning framework, where we recursively approximate the posterior after every task with a Gaussian, leading to a quadratic penalty on changes to the we…
New model generates realistic single-cell gene expression data.
problem Generating realistic single-cell gene expression profiles is challenging.
method scLDM, a latent diffusion model using Diffusion Transformers and linear interpolants.
result Superior performance in generating realistic single-cell gene expression data.
The paper proposes a method to estimate joint probability from unpaired data using entropic transport kernels.
problem Estimating joint probability from unpaired data with unknown internal ordering.
method Maximum-likelihood inference, entropic optimal transport kernels, EMML algorithm.
result The method can recover true density from empirical approximations as the number of blocks increases.
Cheap permutation tests speed up distribution testing without sacrificing accuracy.
problem Efficiently testing distribution differences and independence.
method Group datapoints into bins and permute only these bins, using stored sufficient statistics.
result Cheap permutation tests maintain the accuracy and optimality of standard tests but are significantly faster.
C-OPH improves One Permutation Hashing by using a shorter circulant permutation.
problem Improving the accuracy of One Permutation Hashing (OPH) for Jaccard similarity estimation.
method Develops a new densification method using a shorter circulant permutation.
result Achieves the smallest estimation variance for Jaccard similarity.
Existing deep multitask learning (MTL) approaches align layers shared between tasks in a parallel ordering. Such an organization significantly constricts the types of shared structure that can be learned. The necessity of parallel ordering for deep MTL is first tested by comparing it with permuted ordering of shared la…
Random permutations can offer faster convergence than with-replacement sampling for some functions.
problem Understanding when and how random permutations outperform with-replacement sampling in SGD convergence.
method Analyzing convergence rates for different function classes (1D strongly convex, general strongly convex, quadratic strongly convex).
result The optimal convergence gap between random and permutation-based SGD varies from exponential to nonexistent, depending on the function class.
Representations of sets are challenging to learn because operations on sets should be permutation-invariant. To this end, we propose a Permutation-Optimisation module that learns how to permute a set end-to-end. The permuted set can be further processed to learn a permutation-invariant representation of that set, avoid…
Permutations linked to knots and links, with unknots counted by Schröder numbers.
problem Understanding permutations as knots and links.
method Using grid diagrams and Bennequin's inequality.
result Permutations corresponding to unknots and links are counted by Schröder numbers.
Regularizes RNNs to be invariant to input order.
problem Making RNNs invariant to input order.
method Stochastic regularization to enforce permutation invariance.
result Improves model performance on permutation invariant tasks.
We tackle permutation in linear regression with a new inference framework.
problem Statistical investigation of permutation in linear regression models.
method Localization step followed by conditional Monte Carlo test and coefficient inference.
result Valid statistical inference procedures for permutation and regression coefficients.
Permutability of surface transforms yields discrete analogs.
problem Discretization of smooth surfaces with specific properties.
method Permutability of transforms of smooth surfaces.
result Discrete surfaces with discrete analogs of original properties.
Unified framework for coupled tensor completion improves recovery accuracy.
problem Improving recovery accuracy in coupled tensor completion.
method Unified framework using tensor ring (TR) decomposition with shared latent factors and novel optimization model.
result The proposed method achieves superior recovery accuracy on real-world data compared to state-of-the-art methods.
Interventional data helps identify latent factors without distributional assumptions.
problem Identifying latent factors from interventional data without distributional assumptions.
method Leveraging geometric signatures of latent factors' support from interventional data.
result Latent causal factors can be identified up to permutation and scaling given data from perfect do-interventions.
Recently, the method of b-bit minwise hashing has been applied to large-scale linear learning and sublinear time near-neighbor search. The major drawback of minwise hashing is the expensive preprocessing cost, as the method requires applying (e.g.,) k=200 to 500 permutations on the data. The testing time can also be ex…
New link topology connects permutation discrepancies to Diaconis-Graham inequalities.
problem Characterize permutations for which Diaconis-Graham inequalities hold with equality.
method Relate permutation discrepancies to the Euler characteristic of their associated links.
result Permutation discrepancies are directly related to the Euler characteristic of their associated links.
Additive decoders tackle latent variables and image generation.
problem Latent variables identification and out-of-support image generation in representation learning.
method Additive decoders that can identify latent variables up to permutation and block-wise invertible transformations, and generate novel images by recombining observed factors.
result Additive decoders provide a new setting for nonlinear independent component analysis and can generate novel images by recombining observed factors.
LGB+ improves macroeconomic forecasting by combining linear and tree models.
problem Efficiency in small samples for forecasting with mixed linear and nonlinear dynamics.
method LGB+ is a boosting procedure that evaluates both tree and linear candidates at each step, advancing only the winner. It decomposes forecasts into linear and nonlinear contributions.
result LGB+ delivers strong gains for targets with pronounced autoregressive dynamics or mixed signals.
Graph neural networks improve combinatorial optimization by leveraging inductive bias.
problem Combinatorial optimization problems often arise from related data distributions.
method Using graph neural networks to enhance or solve combinatorial tasks.
result Graph neural networks effectively encode combinatorial and relational input.
We consider a simple and overarching representation for permutation-invariant functions of sequences (or multiset functions). Our approach, which we call Janossy pooling, expresses a permutation-invariant function as the average of a permutation-sensitive function applied to all reorderings of the input sequence. This …
ShuffleNet is a state-of-the-art light weight convolutional neural network architecture. Its basic operations include group, channel-wise convolution and channel shuffling. However, channel shuffling is manually designed empirically. Mathematically, shuffling is a multiplication by a permutation matrix. In this paper, …
We introduce and study the writhe of a permutation, a circular variant of the well-known inversion number. This simple permutation statistics has several interpretations, which lead to some interesting properties. For a permutation sampled uniformly at random, we study the asymptotics of the writhe, and obtain a non-Ga…