Memory-efficient algorithm reduces variance in off-policy RL.
problem High variance in off-policy policy optimization.
method Memory-efficient, stochastically variance-reduced algorithm using off-policy samples.
result Empirically validated effectiveness of the proposed algorithm.
Paper proposes efficient optimizers for large language models with fast convergence and low memory usage.
problem Designing efficient optimizers for large language models with low-memory requirements and fast convergence.
method Structured Fisher information matrix approximation and low-rank extension framework.
result New optimizers (RACS and Alice) achieve better convergence and lower memory usage than existing methods.
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.
State-of-the-art models are now trained with billions of parameters, reaching hardware limits in terms of memory consumption. This has created a recent demand for memory-efficient optimizers. To this end, we investigate the limits and performance tradeoffs of memory-efficient adaptively preconditioned gradient methods.…
New algorithm improves PPS for multi-object matching.
problem Efficiently synchronize partial permutations for multi-object matching.
method Proposed CEMP-Partial algorithm for partial permutation synchronization (PPS). Uses sparse matrix operations and nonconvex weighted projected power method.
result Proves CEMP-Partial can exactly classify corrupted and clean partial permutations under adversarial corruption.
A new memory-efficient Adam variant reduces second moments when feasible.
problem Memory constraints in training machine learning models.
method Signal-to-Noise Ratio (SNR) analysis to identify dimensions where second moments can be replaced by means.
result Memory-efficient Adam variant (SlimAdam) matches performance and stability of Adam while saving up to 98% of second moments.
New methods improve memory efficiency for sampling from complex distributions.
problem Sampling from complex unnormalized distributions over discrete domains.
method Two novel training methods for discrete diffusion samplers.
result Achieve state-of-the-art results in unsupervised combinatorial optimization.
LDAdam optimizes large models with low memory by adapting to lower-dimensional subspaces.
problem Training large models efficiently and accurately.
method Adaptive optimization in lower-dimensional subspaces with a new projection-aware update rule and error feedback mechanism.
result LDAdam achieves accurate and efficient training of language models.
Bayesian histograms achieve optimal distribution estimation with minimal memory usage.
problem Efficiently estimating distributions with minimal memory footprint.
method Bayesian histograms for distribution estimation under Wasserstein distance.
result Bayesian histograms require fewer bins to achieve minimax optimality, reducing memory usage by a polynomial factor.
This work analyzes and optimizes memory and compute costs of learned optimizers.
problem High memory and compute costs of learned optimizers.
method Identified and quantified design features of learned and hand-designed optimizers, constructed a more efficient learned optimizer.
result A learned optimizer that is faster and more memory efficient than previous work.
Lion optimizer performs well in training AI models with memory efficiency.
problem Lion optimizer's theoretical basis is unclear.
method Continuous-time and discrete-time analysis of Lion updates with a new Lyapunov function.
result Lion is a novel and principled approach for constrained optimization.
This work studies low-rank approximation of a positive semidefinite matrix from partial entries via nonconvex optimization. We characterized how well local-minimum based low-rank factorization approximates a fixed positive semidefinite matrix without any assumptions on the rank-matching, the condition number or eigensp…
Improves memory efficiency for meta-learning with large images.
problem High memory usage in meta-learning for few-shot classification.
method LITE: episodic training scheme that decomposes task gradients and back-propagates only a random subset of images.
result Achieves state-of-the-art accuracy on real-world and challenging benchmarks.
Paper proposes low-rank gradient approximation to save memory for deep neural network training.
problem Memory limitation on mobile devices for deep neural network training.
method Approximating gradient matrices using low-rank parameterization.
result Reduces training memory by about 33.0% for Adam optimization and 4.5% relative lower word error rate on ASR personalization task.
SINGD improves KFAC for memory-efficiency and stability in low-precision training.
problem Memory inefficiency and numerical instability of KFAC in low-precision training.
method Formulated inverse-free KFAC update and imposed structures in Kronecker factors.
result SINGD is memory-efficient and numerically robust, often outperforming AdamW in half precision.
A new memory-efficient sign language translation model reduces weight usage.
problem Memory constraints in real-time sign language translation.
method Variational Bayesian sequence-to-sequence network with Gaussian posterior and Indian Buffet Process prior.
result The proposed model achieves substantial weight compression without compromising performance.
AlphaGrad optimizes memory usage in RL algorithms by normalizing gradients.
problem Memory overhead and hyperparameter complexity in adaptive optimizers.
method Tensor-wise L2 normalization followed by a smooth hyperbolic tangent transformation controlled by a single parameter.
result AlphaGrad provides enhanced training stability and competitive performance in various RL algorithms.
PairNets optimize AI models for fast IoT applications.
problem Slow training and high memory usage of deep neural networks.
method Developed Pairwise Neural Networks (PairNets) with low memory and fast training.
result PairNets achieve faster training (one epoch) and lower prediction errors.
This paper optimizes SMPC for neural network inference, reducing memory and time.
problem Memory and time constraints in secure neural network inference.
method Implemented ABY2.0 protocol, optimized memory usage, and used a helper node.
result MNIST inference reduced from 8.03 GB RAM and 200s to 0.2 GB RAM and 32s.
New algorithm learns stable LDSs with lower error and better control performance.
problem Learning stable LDSs from data with minimal reconstruction error and stability constraints.
method Proposes an optimization method using a recent characterization of stable matrices, iteratively improving reconstruction error and ensuring stability.
result Achieves orders-of-magnitude improvement in reconstruction error compared to existing methods.
Improved memory efficiency for deep neural networks.
problem Increasing model size makes deep learning less accessible.
method Inductive-bias-driven network design and manifold-oriented regularization.
result Improved performance and generalization error compared to traditional methods.
CICLAD efficiently mines frequent closed itemsets from data streams with minimal memory usage.
problem Mining frequent closed itemsets from data streams is resource-intensive.
method CICLAD is an intersection-based sliding-window FCI miner that optimizes memory usage while maintaining performance.
result CICLAD achieves significantly lower memory footprint compared to existing methods.
Memory-efficient optimizers fail to track a subspace, leading to unpredictable model performance.
problem Memory-efficient optimizers fail to track a subspace, leading to unpredictable model performance.
method Analyzing the behavior of memory-efficient optimizers like GaLore, which project gradients onto a rank-r subspace recomputed every T steps.
result Memory-efficient optimizers fail to track a subspace, leading to unpredictable model performance.
SketchOGD improves memory efficiency for continual learning.
problem Catastrophic forgetting in continual learning.
method Matrix sketching to compress model gradients.
result SketchOGD outperforms existing memory-efficient OGD variants.
Study proposes memory-efficient backpropagation for linear layers in neural networks.
problem Significant memory usage in backpropagation through linear layers in neural networks.
method Randomized matrix multiplications to reduce memory usage with a moderate decrease in test accuracy.
result Demonstrated benefits of the proposed method on fine-tuning pre-trained models.
PCA reduces language model embeddings to improve speed and memory efficiency.
problem High-dimensional embeddings in RAG models cause scalability issues.
method Used Principal Component Analysis (PCA) to compress embeddings.
result Reducing from 3,072 to 110 dimensions provides significant speedup and memory reduction.
A new method reduces memory requirements for sorting high-dimensional data.
problem Efficiently sorting and organizing high-dimensional data with low memory usage.
method Iteratively shuffles N indices and applies SoftSort optimization steps.
result Significantly improves sorting quality for multidimensional data.
Sketchy reduces memory and compute requirements for adaptive regularization in deep learning.
problem Prohibitive memory and running time for adaptive regularization methods in deep learning.
method Low-rank sketching approach using Frequent Directions (FD) to reduce memory and compute requirements.
result Efficient interpolation between resource requirements and degradation in regret guarantees with rank k. A new RNN model tackles long-time dependencies with fast, invertible, and memory-efficient hidden states.
problem Challenges in processing sequential inputs with long-time dependencies in RNNs.
method A novel RNN architecture based on a Hamiltonian system of oscillators.
result The proposed RNN mitigates exploding and vanishing gradient problems, providing state-of-the-art performance.
Enhances neural architecture search efficiency and prevents performance collapse.
problem Improving memory efficiency and preventing performance collapse in neural architecture search.
method Employing continuous relaxation strategy and gradient-based optimization for over-parameterized BCNN construction, introducing Confident Learning Rate and partial channel connections.
result NAS-v2 delivers state-of-the-art search efficiency on CIFAR-10 and ImageNet.
NeuZip compresses neural network weights to save memory during training and inference.
problem Memory constraints in neural network training and inference.
method Entropy-based dynamic weight compression.
result Significant reduction in memory usage without performance loss.
Efficient sampling reduces memory usage for Minimax distance analysis.
problem Quadratic memory requirement for existing Minimax distance methods.
method Proposes a novel sampling technique with linear space complexity.
result Demonstrates significant reduction in memory usage for Minimax distances.
PipeDream-2BW accelerates large model training by 20x with minimal memory usage.
problem Training large models requires memory beyond single accelerator capacity.
method Pipeline parallelism, weight gradient coalescing, double buffering.
result Accelerates large model training by up to 20x.
Incremental versions of batch algorithms are often desired, for increased time efficiency in the streaming data setting, or increased memory efficiency in general. In this paper we present a novel algorithm for incremental kernel PCA, based on rank one updates to the eigendecomposition of the kernel matrix, which is mo…
New fair PCA method using streaming algorithms with statistical guarantees.
problem Perform PCA while ensuring fair projected distributions.
method Formulated new notion PAFO learnability, proposed fair noisy power method (FNPM) for memory efficiency.
result First statistical guarantee for fair PCA in streaming setting.
XLA compiler extension improves memory efficiency for machine learning.
problem Memory constraints limit the scalability of memory-intensive machine learning algorithms.
method Developed an XLA compiler extension that adjusts algorithm data-flow representation to fit memory limits.
result k-nearest neighbour and sparse Gaussian process regression can be run at larger scales.
LORENZA improves LLM fine-tuning efficiency and generalization.
problem Improving robustness and generalization of LLMs under hardware constraints.
method AdaZo-SAM and LORENZA, combining Adam and SAM with zeroth-order estimation and randomized SVD.
result LORENZA achieves better generalization and reduced memory consumption compared to existing methods.
Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these methods maintain second-order statistics for each parameter, thus introducing significant memory overheads that restrict the size of the model b…
Paper explores weighted averaging schemes for SGD, achieving asymptotic normality and optimality.
problem Improving convergence of SGD in various settings.
method Develops a general weighted averaging scheme for SGD and establishes asymptotic normality.
result Establishes asymptotic normality and optimality of weighted averaged SGD solutions.
Exponential smoothers are a simple and memory efficient way to compute running averages of time series. Here we define and describe practical properties of exponential smoothers for signals observed at constant and variable intervals.
Momentum ResNets improve ResNets' memory efficiency.
problem Memory inefficiency in deep residual neural networks (ResNets).
method Adding a momentum term to the forward rule of ResNets to make them invertible.
result Momentum ResNets can learn any linear mapping up to a multiplicative factor, improving memory efficiency.
New method prevents deep learning models from forgetting past tasks.
problem Catastrophic forgetting in continual learning.
method Direction-constrained optimization (DCO) with autoencoders.
result Model performance is improved without forgetting past tasks.
A new method for statistical inference using SGD under φ-mixing data.
problem Valid statistical inference for time series data with general correlation.
method Proposes a mini-batch SGD estimator and associated mini-batch bootstrap procedure for φ-mixing data. result The proposed method constructs valid confidence intervals for φ-mixing data. Metagenomic studies have increasingly utilized sequencing technologies in order to analyze DNA fragments found in environmental samples.One important step in this analysis is the taxonomic classification of the DNA fragments. Conventional read classification methods require large databases and vast amounts of memory to…
Generative networks trained with sketching reduce computational burden.
problem Computational expense of training generative networks on large datasets.
method Compressive learning using a single sketch vector to approximate Maximum Mean Discrepancy.
result Cost-efficient optimization of generative networks on large datasets.
Efficiently preserves old class knowledge in memory-limited settings.
problem Catastrophic forgetting in class-incremental learning.
method Memory-efficient exemplar preserving scheme and domain-compatible feature extractors.
result Low-fidelity exemplar samples can replace high-fidelity ones with less memory cost.
Flora uses random projections to achieve high-rank updates with low memory usage.
problem Excessive memory usage in large neural networks during training.
method Flora approximates LoRA using random projections to enable high-rank updates with sublinear space complexity.
result Flora achieves high-rank updates with significantly reduced memory usage compared to LoRA.
We present a novel algorithm, Westfall-Young light, for detecting patterns, such as itemsets and subgraphs, which are statistically significantly enriched in one of two classes. Our method corrects rigorously for multiple hypothesis testing and correlations between patterns through the Westfall-Young permutation proced…