Memory-efficient learning for large-scale imaging systems.
problem Memory limitations in GPUs for real-world large-scale inverse problems.
method Exploits reversibility of network layers to enable data-driven design.
result Demonstrated on small-scale and large-scale real-world systems.
Efficient knockoffs for large-scale feature selection.
problem Large-scale feature selection problems.
method Gaussian model-X knockoffs with efficient methods for solving semidefinite programs.
result Efficient knockoffs can be generated with linear complexity in the dimension.
Paper presents an efficient algorithm for learning minimax risk classifiers with large-scale data.
problem Efficient learning of minimax risk classifiers for large-scale data with multiple classes.
method Combination of constraint and column generation for efficient learning.
result 10x speedup for general large-scale data and 100x speedup with many classes.
We derive scaling laws for optimizing neural networks in hardware.
problem Optimizing the large parameter space of neural networks in hardware.
method Analytical derivation of scaling laws for Coordinate Descent optimization.
result Convergence is exponential and scales linearly with the number of neurons.
A new kernel, Isolation Kernel, simplifies large scale online kernel learning without sacrificing accuracy.
problem Building efficient and scalable kernel-based models from large datasets with high accuracy.
method Introducing Isolation Kernel, which creates an exact, sparse, and finite-dimensional feature map of a kernel, allowing for efficient large scale online kernel learning without accuracy loss.
result Large scale online kernel learning can be achieved efficiently and accurately using Isolation Kernel.
Serverless runtimes boost large-scale optimization efficiency.
problem Efficiently solving large-scale optimization problems.
method Master-worker setup with AWS Lambda, parallel optimization algorithm.
result Relative speedups up to 256 workers and efficiencies above 70% up to 64 workers.
CauScale efficiently discovers causal relationships in large graphs.
problem Efficiency bottlenecks in causal discovery for large graphs.
method Neural architecture with reduction unit and tied attention weights.
result Achieves 99.6% mAP on in-distribution data and 84.4% on out-of-distribution data.
Cascade-BGNN efficiently learns node representations for large-scale bipartite graphs.
problem Efficiently learning node representations for large-scale bipartite graphs with limited labels.
method Cascade-BGNN uses customized Inter-domain Message Passing (IDMP) and Intra-domain Alignment (IDA) for efficient information aggregation.
result Cascade-BGNN achieves domain-consistent, self-supervised, and efficient node representation learning.
Efficiently computes tree-Wasserstein barycenter for large-scale multilevel clustering and scalable Bayes.
problem Large-scale multilevel clustering and scalable Bayes problems.
method Proposes an efficient algorithm for tree-Wasserstein barycenter and variants.
result Significantly improves efficiency in computation and memory usage for large-scale applications.
MEMe efficiently approximates large-scale ML problems with hundreds of moments.
problem Efficient approximation in large-scale machine learning.
method Maximum entropy algorithm with hundreds of moments for computationally efficient approximations.
result Superior to existing approaches in fast log determinant estimation and Bayesian optimisation.
Efficiently scales continuous kernels with sparse Fourier domain learning.
problem High computational and memory demands, spectral bias in continuous kernels.
method Sparse learning in the Fourier domain.
result Efficient scaling of continuous kernels, reduced computational and memory requirements, mitigated spectral bias.
Study shows Direct Feedback Alignment fails to offer more efficient scaling than backpropagation.
problem Understanding and optimizing training methods for neural networks.
method Use of scaling laws to compare Direct Feedback Alignment (DFA) and backpropagation.
result DFA fails to offer more efficient scaling than backpropagation.
Improves diffusion model performance and efficiency through classical search.
problem Tackles inference-time control in diffusion models.
method Proposes a framework combining local and global search for efficient navigation.
result Significant gains in performance and efficiency across various domains.
Efficiently solves large-scale robust portfolio optimization problems.
problem High computational demands in large-scale robust portfolio optimization.
method Extended supporting hyperplane approximation for distributionally robust portfolio problems.
result Significantly reduces computational time from several thousand seconds to just a few.
MSNet uses high frequency residual learning for efficient multi-scale image classification.
problem Efficient multi-scale image classification for mobile and embedded devices.
method Two network architecture: low resolution for low frequency, high resolution for high frequency residuals.
result MSNet achieves significant accuracy improvements over different base networks.
Efficiently selects nearest neighbors for labeling to speed up active learning.
problem Intractable active learning and search for large-scale unlabeled data.
method Restricts candidate pool to nearest neighbors of labeled set.
result Achieved similar performance to global approach but reduced computational cost by up to 3 orders of magnitude.
Blend-ASC improves self-consistency efficiency by dynamically allocating samples, reducing costs.
problem Efficiently applying self-consistency to large datasets is computationally expensive.
method Blend-ASC dynamically allocates samples during inference, improving efficiency.
result Blend-ASC reduces sample usage by 6.8x on average compared to vanilla self-consistency.
ASRNN adapts scales dynamically for better sequence modeling.
problem Fixed scales in multiscale RNNs don't match temporal patterns.
method Adaptively learns and adjusts scales based on temporal contexts.
result ASRNNs yield better performances with dynamical scaling.
Scaling laws for neural language models reveal optimal model size and compute allocation.
problem Understanding the optimal model size and compute allocation for neural language models.
method Empirical analysis of scaling laws for cross-entropy loss across model size, dataset size, and compute.
result Simple equations govern the dependence of overfitting and training speed on model/dataset size and model size, respectively.
This paper tackles hyperparameter tuning for large-scale kernel ridge regression.
problem Hyperparameter tuning is crucial but often left to users, hindering efficiency and usability.
method Proposes a complexity regularization criterion based on a data-dependent penalty for efficient optimization.
result Demonstrates the benefit of the proposed approach through extensive empirical evaluation.
Predicts language model performance from public models without training.
problem Understanding how language model performance varies with scale.
method Observational approach building scaling laws from publicly available models.
result Smooth, sigmoidal behavior of emergent phenomena is predictable from small models.
WaveletNet improves edge device efficiency with logarithmic convolution.
problem Efficiency and performance on edge devices for CNNs.
method Introduces WaveletNet architecture with wavelet convolution and depthwise fast wavelet transform.
result WaveletNet achieves superior and comparable performance to state-of-the-art models on CIFAR-10 and ImageNet.
Tensor networks reveal limitations for efficient text description but suggest potential for images.
problem Efficiently describing large text and image data sets using tensor networks.
method Investigation of mutual information scaling, introduction of mutual information estimators, and use of autoregressive and convolutional neural networks.
result Text data cannot be efficiently described by 1D tensor networks, while images may be better described by 2D tensor networks.
Improves RLHF sample efficiency by scaling reward complexity polynomially.
problem Exponential sample complexity in RLHF algorithms for skewed preferences.
method SE-POPO, an online RLHF algorithm that achieves polynomial sample complexity.
result SE-POPO outperforms existing algorithms in sample efficiency.
Three methods for tuning HMC diagonal scale matrices compared.
problem Improving Hamiltonian Monte Carlo efficiency with diagonal scale matrices.
method Three approaches: ISG, median crossing frequency, and estimated marginal standard deviations.
result ISG method leads to more efficient sampling in many cases.
Bayesian model tackles high-dimensional inverse problems efficiently.
problem Estimating spatially-varying parameters in expensive models.
method Multiscale Bayesian inference with deep generative models and MCMC.
result Efficient estimation of global and local parameter features.
New method speeds up learning of complex dynamical systems.
problem Efficiently learning large-scale dynamical systems from finite data.
method Random projections (sketching) to boost kernel-based Koopman operator estimators.
result The proposed estimators maintain accuracy while significantly reducing computation time.
Efficiently projects points onto polytopes, especially useful in web-scale applications.
problem Efficiently projecting points onto polytopes in large-scale applications.
method Developed a vertex-oriented incremental algorithm for polytope projection, tailored for simplex and unit-box cut polytopes.
result Majority of projections lie on vertices of polytopes, leading to significant performance improvements.
Hierarchical Softmax approximates class probabilities for large datasets efficiently.
problem Computational inefficiency of Softmax for large-scale classification tasks.
method Used Hierarchical Softmax to approximate class probabilities efficiently.
result Hierarchical Softmax performance degrades as the number of classes increases.
The paper studies scaling laws for associative memory mechanisms.
problem Understanding and optimizing learning and memorization processes.
method High-dimensional matrices of outer products of embeddings, relating to transformer models. Derived scaling laws with sample and parameter sizes. Extensive numerical experiments.
result Precise scaling laws and statistical efficiency of estimators.
Study finds market inefficiencies vary by time scale, with news uncertainty key.
problem Evaluating scale-dependent informational efficiency of stock markets.
method Tensor-eigenvalue-based Financial Chaos Index, Granger causality, network analysis.
result Semi-strong form of EMH rejected at daily frequency, but not at monthly.
DistPre predicts traffic speeds efficiently for large networks.
problem Fine-grained, accurate speed prediction for large-scale transportation networks.
method Customizes LSTM models on a cluster, sharing trained models between detectors.
result Efficient and accurate fine-grained traffic-speed prediction.
Efficiently performs PCA on large datasets using Nyström sampling.
problem Efficiently performing kernel PCA on large datasets.
method Nyström sampling to improve computational efficiency.
result Nyström sampling improves PCA efficiency without sacrificing statistical accuracy.
Bayesian batch active learning approximates model parameters efficiently.
problem High label acquisition cost for large-scale supervised models.
method Sparse subset approximation using Bayesian active learning.
result Efficient active learning at scale with diverse batches.
Efficiently decomposes large tensors using stochastic gradients.
problem Efficiently decomposing large tensors for multiway data analysis.
method Stochastic gradients computed via MTTKRP kernel for efficient computation.
result Advantages and scalability demonstrated for large-scale problems.
A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to combinatorial constraints, and then observes stochastic weights of these items and receives their sum as a payoff. In this paper, we consider efficient learning in large-s…
The paper shows how to efficiently generate large Gaussian process samples with reliability guarantees.
problem Generating large-scale Gaussian process samples efficiently and with reliability.
method Demonstrates scaling data generation to large \(n\) while providing high probability guarantees.
result Efficiently generates large Gaussian process samples with reliability guarantees.
String kernels are attractive data analysis tools for analyzing string data. Among them, alignment kernels are known for their high prediction accuracies in string classifications when tested in combination with SVM in various applications. However, alignment kernels have a crucial drawback in that they scale poorly du…
CAFLOW uses auto-regressive flows to translate images efficiently.
problem Image-to-image translation tasks.
method Transforms conditioning image into latent encodings using normalizing flows, models conditional distribution with auto-regressive distributions.
result Outperforms former conditional flow designs.
NetSMF efficiently embeds large networks by sparse matrix factorization.
problem Learning latent representations for large-scale networks efficiently.
method NetSMF leverages spectral sparsification to efficiently sparsify and factorize a dense matrix.
result NetSMF achieves high efficiency and effectiveness on large-scale networks.
Paper tackles leverage effect estimation from noisy data.
problem Estimating leverage effect from high-frequency data with microstructure noise.
method Holistic multi-scale framework operating directly on leverage effect, using Subsampling-and-Averaging Leverage Effect (SALE) and Multi-Scale Leverage Effect (MSLE) estimators.
result Holistic multi-scale framework achieves substantial efficiency gains over existing benchmarks.
Efficiently trains large-scale ordinal regression models using DCD.
problem Efficiently training large-scale ordinal regression models.
method Dual coordinate descent method (DCD) for training and a new prediction function.
result Extensive experiments show the DCD method is suitable for large-scale data.
Paper proposes data quality measures for large-scale high-dimensional data.
problem Lack of practical data quality measures for large-scale high-dimensional data.
method Proposes two data quality measures: class separability and in-class variability. Efficient algorithms based on random projections and bootstrapping are provided.
result Efficient algorithms for computing data quality measures on large-scale high-dimensional data.
New research shows shrinkage methods re-scale portfolio efficient frontiers under distributional misspecification.
problem Poor performance of mean-variance portfolio decisions under distributional assumptions.
method Investigation of shrinkage methods under different distributional assumptions (auto-correlation, skewness, excess kurtosis).
result Shrinkage methods re-scale the sample efficient frontier, implying standard comparison methods are flawed.
PALMS reconstructs large-scale networks efficiently with parallel computing.
problem Reconstructing large-scale latent networks from observed dynamics is computationally challenging.
method PALMS (Parallel Adaptive Lasso with Multi-directional Signals) framework for distributed network reconstruction.
result PALMS substantially reduces computational complexity and storage requirements.
This paper surveys large-scale machine learning methods for efficient data analysis.
problem Efficiently processing large-scale data with machine learning models.
method Divided into three categories: model simplification, optimization approximation, and computation parallelism.
result Blueprint for future developments in large-scale machine learning.
Efficient algorithms for large Maxent models improve wildfire probability predictions.
problem Training large-scale, non-smooth Maxent models efficiently for big data.
method First-order optimization algorithms using Kullback-Leibler divergence.
result Our algorithms outperform state-of-the-art methods by one order of magnitude.
New framework explains how larger pre-trained models reduce downstream learning sample complexity.
problem Understanding why larger pre-trained models reduce sample complexity in downstream tasks.
method Introducing a novel framework called Caulking inspired by PEFT methods.
result Improved pre-trained models provably decrease downstream task sample complexity.