Paper studies non-tight reconstruction threshold in a 4-state model with different in/out block mutations.
problem Non-tight reconstruction threshold in a 4-state symmetric model with different in-block and out-block mutations.
method Inspired by the q1+q2 stochastic block model, rigorously analyzes conditions for non-tightness of the reconstruction threshold. result Rigorously gives conditions for the non-tightness of the reconstruction threshold in a 4-state symmetric model.
Nonnegative CANDECOMP/PARAFAC (NCP) decomposition is an important tool to process nonnegative tensor. Sometimes, additional sparse regularization is needed to extract meaningful nonnegative and sparse components. Thus, an optimization method for NCP that can impose sparsity efficiently is required. In this paper, we co…
We decode latent states in Block MDPs and learn near-optimal policies.
problem Model estimation and reward-free learning in Block MDPs.
method Information-theoretical lower bound and efficient model estimation algorithm.
result Our algorithm approaches the information-theoretical limit for latent state decoding and converges to optimal policies.
This study explains why approximate NGD works well in wide neural networks.
problem Understanding why NGD with approximate Fisher information converges fast in wide neural networks.
method Analyzing asymptotic training dynamics in function space via the neural tangent kernel.
result NGD with approximate Fisher information achieves the same fast convergence as exact NGD under specific conditions.
Improved RL in BMDPs reduces regret to O(sqrt(T)+n).
problem Real-world RL challenges due to large state and action spaces.
method Two-phase RL algorithm: latent structure learning followed by adaptive strategy.
result Achieves asymptotically optimal regret O(sqrt(T)+n).
Community detection is a fundamental unsupervised learning problem for unlabeled networks which has a broad range of applications. Many community detection algorithms assume that the number of clusters r is known apriori. In this paper, we propose an approach based on semi-definite relaxations, which does not require…
The performance of sparse signal recovery from noise corrupted, underdetermined measurements can be improved if both sparsity and correlation structure of signals are exploited. One typical correlation structure is the intra-block correlation in block sparse signals. To exploit this structure, a framework, called block…
In this work we apply variations of ResNet architecture to the task of atrial fibrillation classification. Variations differ in number of filter after first convolution, ResNet block layout, number of filters in block convolutions and number of ResNet blocks between downsampling operations. We have found a range of mod…
Machine learning portfolios perform well with simple imputation of missing data.
problem Handling missing values in machine learning portfolios constructed from cross-sectional return predictors.
method Simple imputation with cross-sectional means compared to rigorous expectation-maximization methods.
result Simple imputation performs well due to the structure of missing data.
We present asymptotic and finite-sample results on the use of stochastic blockmodels for the analysis of network data. We show that the fraction of misclassified network nodes converges in probability to zero under maximum likelihood fitting when the number of classes is allowed to grow as the root of the network size …
The paper uses deep learning to detect financial market regimes from correlation matrices.
problem Detecting financial market regimes from correlation dynamics.
method Representation learning on block hierarchical SPD correlation matrices using SPDNet, SPD-NetBN, and U-SPDNet models.
result Deep learning models overfit in financial market data, misleading performance metrics.
Biclustering structures in data matrices were first formalized in a seminal paper by John Hartigan (1972) where one seeks to cluster cases and variables simultaneously. Such structures are also prevalent in block modeling of networks. In this paper, we develop a unified theory for the estimation and completion of matri…
Alexandrov spaces with non-negative curvature are characterized by the matrix displacement convexity of an entropy tensor.
problem Characterizing non-negative curvature in Alexandrov spaces
method Constructing a parallel trivialization of the entropy tensor
result The entropy tensor is matrix displacement convex on Alexandrov spaces
Optimal spectral method found for inhomogeneous spiked Wigner model.
problem Structured noise in learning scenarios.
method Random matrix theory and spectral analysis.
result Optimal threshold for phase transition in block-structured Wigner model.
We propose two spectral algorithms for partitioning nodes in directed graphs respectively with a cyclic and an acyclic pattern of connection between groups of nodes. Our methods are based on the computation of extremal eigenvalues of the transition matrix associated to the directed graph. The two algorithms outperform …
New GCNs improve graph classification with deeper multi-scale information.
problem Limited expressive power of existing GCNs.
method Generalized spectral graph convolution and deep GCN architectures, showing equivalence under certain conditions.
result Two new architectures achieve better performance on node classification tasks.
We propose a general algorithmic framework for constrained matrix and tensor factorization, which is widely used in signal processing and machine learning. The new framework is a hybrid between alternating optimization (AO) and the alternating direction method of multipliers (ADMM): each matrix factor is updated in tur…
Study examines stylized facts in DEX markets vs. traditional exchanges.
problem Comparing stylized facts in decentralized exchanges (DEXs) vs. traditional markets.
method Empirical analysis of 24 most active Uniswap v3 pools.
result New statistical regularities in DEX markets, linked to market structure and activity.
New method relaxes PCA orthogonality constraints using explained variance of correlated components.
problem Difficulty in using PCA for sparse design due to orthogonality constraints and non-differentiable penalty.
method Introduce expvar(Y) to measure variance explained by correlated components, relax orthogonality constraints.
result Two expvar(Y) definitions suitable for block PCA formulations without orthogonality constraints.
We describe an adaptation of the simulated annealing algorithm to nonparametric clustering and related probabilistic models. This new algorithm learns nonparametric latent structure over a growing and constantly churning subsample of training data, where the portion of data subsampled can be interpreted as the inverse …
Proposes method to learn state abstractions that generalize across environments.
problem Learning abstractions that generalize in block MDPs.
method Invariant causal prediction to learn model-irrelevant state abstractions (MISA).
result Proves high probability of outputting a state abstraction corresponding to causal feature set for return.
New deep learning model robust to adversarial attacks using stochastic LWTA units.
problem Adversarial robustness in deep learning networks.
method Introduces deep networks with stochastic LWTA activations, combining them with Bayesian non-parametric tools.
result Achieves high robustness to adversarial perturbations, outperforming state-of-the-art methods.
Method estimates number of clusters in Block Markov Chain trajectories.
problem Challenges in choosing number of clusters for sequential data.
method Spectral embedding and density-based clustering.
result Asymptotically consistent method for estimating clusters.
A new framework solves complex optimization problems with continuous worst-case distributions.
problem Optimizing under uncertain distributions with continuous worst-case scenarios.
method Flow-based distributionally robust optimization (DRO) with Wasserstein uncertainty sets and invertible transport maps.
result The framework finds continuous worst-case distributions and samples efficiently.
Generative synthetic data can preserve predictive accuracy but distort causal inference.
problem Distortion of average treatment effect estimates in synthetic data.
method Hybrid synthetic-data framework that generates covariates while modeling treatment and outcome mechanisms separately.
result Hybrid synthesis improves causal fidelity compared to fully generative baselines.
Generative grading improves automated feedback for structured problems.
problem Difficulty in providing high-quality feedback on structured assignments.
method Generative descriptions of student cognition, probabilistic programs, and learning to infer feedback.
result Achieved near-human accuracy in grading and feedback across diverse domains.
Generative Adversarial Network purifies images from steganography without degrading quality.
problem Destruction of image steganography while maintaining visual quality.
method Generative Adversarial Network (GAN) optimized for steganography destruction.
result High rate of steganographic content destruction with minimal visual quality degradation.
Nonconvex and nonsmooth optimization problems are frequently encountered in much of statistics, business, science and engineering, but they are not yet widely recognized as a technology in the sense of scalability. A reason for this relatively low degree of popularity is the lack of a well developed system of theory an…
A new method for state space partitioning in block particle filtering reduces bias and variance.
problem Overcoming the curse of dimensionality in non-linear, non-Gaussian state space estimation.
method Formulates state space partitioning as a clustering problem and uses spectral clustering with constraints.
result The proposed method effectively groups correlated state variables into smaller blocks, reducing bias and variance.
New model handles complex non-linear relationships with hidden graph structures.
problem Modeling non-linear relationships with hidden graph-structured interactions.
method Block-diagonal localized mixture of polynomial experts (BLoMPE) regression model with penalized maximum likelihood selection criterion.
result Strong theoretical guarantee for finite-sample oracle inequality.
Several studies explore inferences based on stochastic volatility (SV) models, taking into account the stylized facts of return data. The common problem is that the latent parameters of many volatility models are high-dimensional and analytically intractable, which means inferences require approximations using, for exa…
Paper predicts transaction confirmation time in Ethereum blockchain using machine learning.
problem Estimating transaction confirmation time in Ethereum blockchain.
method Uses machine learning, specifically Random Forest Regressor and Multilayer Perceptron, to predict transaction confirmation time.
result Proposed model shows improved accuracy in predicting transaction confirmation time compared to statistical models.
New algorithm learns sparse linear MDPs with polynomial interactions, improving sample complexity.
problem Learning optimal policies in sparse linear MDPs with limited interactions and unknown features.
method Developed a polynomial-time algorithm using feature selection and emulator for sparse linear MDPs.
result First polynomial-time algorithm for learning near-optimal policies in k-sparse linear MDPs.