DiffusionBlocks trains neural networks by breaking them into independent blocks, reducing memory usage.
problem Memory bottlenecks in end-to-end neural network training.
method Transforming transformer-based networks into independent trainable blocks via a denoising process.
result Independent block-wise training matches end-to-end training performance while reducing memory requirements.
BlockEcho method improves imputation of block-wise missing data.
problem Block-wise missing data reduces interpolation capability and predictive power.
method Integrates Matrix Factorization (MF) within Generative Adversarial Networks (GAN) to retain long-distance inter-element relationships.
result Superior performance on public datasets across three domains, especially at higher missing rates.
Extreme multi-label classification aims to learn a classifier that annotates an instance with a relevant subset of labels from an extremely large label set. Many existing solutions embed the label matrix to a low-dimensional linear subspace, or examine the relevance of a test instance to every label via a linear scan. …
Knowledge distillation (KD) is a popular method for reducing the computational overhead of deep network inference, in which the output of a teacher model is used to train a smaller, faster student model. Hint training (i.e., FitNets) extends KD by regressing a student model's intermediate representation to a teacher mo…
Neural networks have achieved state of the art performance across a wide variety of machine learning tasks, often with large and computation-heavy models. Inducing sparseness as a way to reduce the memory and computation footprint of these models has seen significant research attention in recent years. In this paper, w…
Improved EXACT strategy reduces GNN memory consumption and runtime.
problem Efficiently training large-scale GNNs with reduced memory usage.
method Block-wise quantization of intermediate activation maps with improved variance minimization.
result Further reduction in memory consumption (>15%) and runtime speedup (5%) with similar performance trade-offs.
New algorithms solve complex minimax problems without needing derivatives.
problem Solving nonconvex-concave minimax problems efficiently.
method Zeroth-order alternating and proximal gradient algorithms.
result Iteration complexity and function value estimation bounds established.
Paper proposes protecting DNN models with secret key preprocessing.
problem Protecting deep learning models from unauthorized access.
method Block-wise pixel shuffling with secret key for preprocessing.
result Protected models maintain close performance to non-protected models with correct key, but accuracy drops significantly with incorrect key.
Paper proposes an algorithm for robust estimation using Huber's criterion.
problem Non-convexity and non-robustness of joint maximum likelihood estimation.
method Block-wise minimization majorization framework with data-adaptive step sizes.
result Improved convergence and robustness in sparse learning.
Existing MAP inference algorithms for determinantal point processes (DPPs) need to calculate determinants or conduct eigenvalue decomposition generally at the scale of the full kernel, which presents a great challenge for real-world applications. In this paper, we introduce a class of DPPs, called BwDPPs, that are char…
New defense method inspired by encryption improves visual classification accuracy.
problem Conventional defenses reduce accuracy and are defeated by obfuscated gradients.
method Block-wise pixel shuffling with secret key for training and test images.
result Achieves high accuracy (91.55%) on clean images and (89.66%) on adversarial examples.
We consider the problem of metric learning for multi-view data and present a novel method for learning within-view as well as between-view metrics in vector-valued kernel spaces, as a way to capture multi-modal structure of the data. We formulate two convex optimization problems to jointly learn the metric and the clas…
A new model uses attention and Gaussian processes for efficient time-series generation.
problem Computational inefficiency and uncertainty underestimation in sequence transduction.
method Attention-based Gaussian process network for real-valued sequence generation.
result The model improves training efficiency and learns factorized generative distribution.
We propose a penalized likelihood method to jointly estimate multiple precision matrices for use in quadratic discriminant analysis and model based clustering. A ridge penalty and a ridge fusion penalty are used to introduce shrinkage and promote similarity between precision matrix estimates. Block-wise coordinate desc…
We propose an approach to reduce the bias of ridge regression and regularization kernel network. When applied to a single data set the new algorithms have comparable learning performance with the original ones. When applied to incremental learning with block wise streaming data the new algorithms are more efficient due…
AdapDISCOM tackles high-dimensional multimodal data with missingness and errors, improving prediction and biomarker selection.
problem High-dimensional multimodal data with block-wise missingness and measurement errors.
method AdapDISCOM introduces modality-specific weighting schemes to address heterogeneity and error magnitudes.
result AdapDISCOM consistently outperforms existing methods under heterogeneous contamination and heavy-tailed distributions.
This paper proposes network recasting as a general method for network architecture transformation. The primary goal of this method is to accelerate the inference process through the transformation, but there can be many other practical applications. The method is based on block-wise recasting; it recasts each source bl…
Generative model tackles inconsistent attributes across datasets by enabling precise conditional generation.
problem Inconsistent attributes across merged datasets limit controllability in conditional generative modeling.
method Diffusion Model with Double Guidance, maintaining control over multiple conditions without joint annotations.
result Outperforms baselines in molecular and image generation tasks, aligning with target distributions and controlling missing conditions.
Incorporating deep neural networks in image compressive sensing (CS) receives intensive attentions in multimedia technology and applications recently. As deep network approaches learn the inverse mapping directly from the CS measurements, the reconstruction speed is significantly faster than the conventional CS algorit…
JKO-iFlow uses neural ODEs to improve generative models with reduced memory and training complexity.
problem Efficiently training deep generative models in high dimensions with reduced memory and training complexity.
method JKO scheme inspired neural ODE flow network with adaptive time reparameterization.
result JKO-iFlow achieves competitive performance compared to existing models at reduced computational and memory cost.
Proposes BONMI for integrating noisy matrices from multi-source data.
problem Integrating noisy matrices from multi-source data with block-wise missingness.
method Exploits orthogonal Procrustes problem to align eigenspaces and completes missing blocks.
result Statistical rate for eigenspace of underlying matrix comparable to independently missing assumption.
Improved Mamba model for long-range sequence tasks.
problem Mamba's poor performance on long-range sequential tasks.
method Proposed B2S6, combining block-wise selective dynamics and channel-specific bias.
result Empirically, B2S6 outperforms S4 and S4D on LRA tasks.
Latent Block-Diffusion Temporal Point Processes (LBDTPP) is a semi-autoregressive framework for generating asynchronous event sequences.
problem Generating asynchronous event sequences
method Latent Block-Diffusion Temporal Point Processes
result Outperforms state-of-the-art TPP baselines in both unconditional and conditional generation tasks
Training-free method improves large language model sequence quality via reward-guided sampling.
problem Optimizing large language model sequence quality over token likelihood.
method Reward-augmented target distribution combined with Sequential Monte Carlo sampling.
result Significant gains in sequence generation and mathematical reasoning tasks.
This paper revisits the classic iterative proportional scaling (IPS) from a modern optimization perspective. In contrast to the criticisms made in the literature, we show that based on a coordinate descent characterization, IPS can be slightly modified to deliver coefficient estimates, and from a majorization-minimizat…
New algorithm improves distributed SGD with random sparsification for better convergence and generalization.
problem Communication bottleneck in distributed deep learning.
method Proposes detached error feedback (DEF) algorithm to improve convergence and generalization of communication-efficient distributed SGD.
result Shows better convergence and generalization bounds than existing methods.
Study improves neural network performance in sequential learning for image classification.
problem Improving neural network performance in sequential learning for image classification.
method Evaluation of approaches for computing prequential description lengths, proposing forward-calibration and replay-streams.
result Improved description lengths for image classification datasets, outperforming previous results.
Sequential coordinate ascent is more robust in high-dimensional linear regression.
problem Behavior difference between sequential and parallel coordinate ascent in variational inference.
method Comparison of sequential and parallel coordinate ascent algorithms in high-dimensional linear regression.
result Sequential algorithm converges under more relaxed conditions than parallel algorithm.
Paper proposes a new method for estimating conditional densities using logistic regressions.
problem Estimating conditional densities for complex distributions.
method Parametric conditional density estimation via weighted logistic regressions.
result Maximum likelihood estimates can be obtained efficiently via a block-wise alternating maximization scheme and local case-control sampling.
Novel algorithm speeds up log-determinant estimation for large matrices.
problem Efficiently estimating log-determinants of large positive definite matrices under memory constraints.
method Hierarchical algorithm based on block-wise computation of LDL decomposition.
result Accurate estimation of NTK log-determinants from a tiny fraction of the full dataset.
Finding an embedding space for a linear approximation of a nonlinear dynamical system enables efficient system identification and control synthesis. The Koopman operator theory lays the foundation for identifying the nonlinear-to-linear coordinate transformations with data-driven methods. Recently, researchers have pro…
The group lasso is a penalized regression method, used in regression problems where the covariates are partitioned into groups to promote sparsity at the group level. Existing methods for finding the group lasso estimator either use gradient projection methods to update the entire coefficient vector simultaneously at e…
Develops large-sample theory for non-stationary source separation.
problem Lack of large-sample results for non-stationary source separation methods.
method Large-sample theory for NSS-JD method under specific assumptions.
result Consistency of unmixing estimator and its convergence to Gaussian distribution.
Paper studies tensor models using random matrix theory.
problem Analyzing asymmetric order-d spiked tensor models with Gaussian noise.
method Uses variational definition of singular vectors and values, constructs equivalent spiked symmetric block-wise random matrix from tensor contractions.
result Characterizes asymptotic singular values and alignments of singular vectors with true spike components.
Proposes a new algorithm to estimate invariant subspaces across multilayer networks.
problem Estimating invariant subspaces across heterogeneous multiple networks.
method Bias-corrected joint spectral embedding algorithm that recursively calibrates diagonal bias and iteratively updates the subspace estimator.
result Established entrywise subspace perturbation bound and entrywise eigenvector central limit theorem for the algorithm.
Asynchronous federated modeling improves spatial data sharing without centralizing raw data.
problem Privacy and bandwidth constraints in distributed spatial data.
method Asynchronous federated modeling using low-rank Gaussian process approximations with block-wise optimization and adaptive strategies.
result Asynchronous federated modeling achieves synchronous performance and outperforms it in heterogeneous settings.
Categorical regressor variables are usually handled by introducing a set of indicator variables, and imposing a linear constraint to ensure identifiability in the presence of an intercept, or equivalently, using one of various coding schemes. As proposed in Yuan and Lin [J. R. Statist. Soc. B, 68 (2006), 49-67], the gr…
Paper proposes an efficient algorithm for learning sparse Bayesian networks from discrete high-dimensional data.
problem Learning sparse structure Bayesian networks from high-dimensional discrete data.
method Score function for sparse DAG, block-wise stochastic coordinate descent with variance reduction.
result The proposed algorithm outperforms existing methods in synthetic data benchmarks.
CN-SBM clusters cancer samples and regions based on copy number variants.
problem Clonal evolution in cancer monitored by noisy copy number variants.
method Probabilistic framework using bipartite categorical block model.
result Improved model fit and clinically relevant subtypes identified.
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. 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.
New framework models non-exchangeable networks with latent orders and graphons.
problem Modeling non-exchangeable network data with complex dependencies.
method Latent orders and graphon-based approach for adjacency matrix probabilities.
result Consistent estimation and clustering of latent network structure.
The characteristics (or numerical patterns) of a feature vector in the transform domain of a perturbation model differ significantly from those of its corresponding feature vector in the input domain. These differences - caused by the perturbation techniques used for the transformation of feature patterns - degrade the…
Efficient SVD algorithm robust to outliers.
problem Outliers in data matrix affect SVD accuracy and speed.
method Spherically Normalized SVD (SpherSVD) algorithm.
result Significantly faster and more robust than existing methods.
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.
Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses. As a case study, a state-of-the-art neural language model usually consists of one or more recurrent layers sandwiched between an embedding layer used for representing inp…
The min-max problem, also known as the saddle point problem, is a class of optimization problems which minimizes and maximizes two subsets of variables simultaneously. This class of problems can be used to formulate a wide range of signal processing and communication (SPCOM) problems. Despite its popularity, most exist…
MAGIC uncovers disease heterogeneity across brain scales.
problem Understanding distinct subtypes of brain diseases at different spatial scales.
method Multi-scale Heterogeneity Analysis and Clustering (MAGIC) using semi-supervised clustering.
result Two main subtypes of AD identified with distinct atrophy patterns.