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.
FPG uses fractional calculus for efficient reinforcement learning with long-term memory.
problem High variance and inefficient sampling in standard policy gradient methods for long-term temporal modeling.
method Fractional Policy Gradients (FPG) incorporating Caputo fractional derivatives for power-law temporal correlations.
result Achieves asymptotic variance reduction of order O(t^(-alpha)) and sample efficiency gains.
The Long-Short-Term-Memory Recurrent Neural Networks (LSTM RNNs) are a popular class of machine learning models for analyzing sequential data. Their training on modern GPUs, however, is limited by the GPU memory capacity. Our profiling results of the LSTM RNN-based Neural Machine Translation (NMT) model reveal that fea…
The well-known Mori-Zwanzig theory tells us that model reduction leads to memory effect. For a long time, modeling the memory effect accurately and efficiently has been an important but nearly impossible task in developing a good reduced model. In this work, we explore a natural analogy between recurrent neural network…
DSG activates only a small amount of neurons for efficient deep learning.
problem Efficient deployment of deep neural networks on embedded devices.
method Dynamic and sparse graph structure with dimension-reduction search and double-mask selection.
result Significant memory saving (1.7-4.5x) and operation reduction (2.3-4.4x) with little accuracy loss.
New deep ESN architectures improve memory capacity and prediction accuracy.
problem Improving memory capacity and prediction accuracy of ESNs.
method Two new deep ESN architectures: parallel and series. Analysis of memory capacity and prediction accuracy.
result Parallel deep ESNs have equivalent memory capacity to shallow ESNs, while series deep ESNs have smaller memory capacity.
We design and study a Contextual Memory Tree (CMT), a learning memory controller that inserts new memories into an experience store of unbounded size. It is designed to efficiently query for memories from that store, supporting logarithmic time insertion and retrieval operations. Hence CMT can be integrated into existi…
KineticSim: A lightweight, high-performance execution engine for real-time market simulators
problem Simulating financial markets at scale with multi-agent models
method Reusable parallel design pattern: persistent, state-carrying clearing for iterative multi-agent reductions
result Reduces per-step critical-path depth from Theta(L+A) to Theta(log L + ceil(A/L))
SRG improves optimization efficiency with reduced memory and computation overhead.
problem Limited applicability of variance-reduced optimization algorithms.
method SRG (stochastic reweighted gradient) using importance sampling.
result SRG outperforms SGD and provably improves convergence in strongly-convex cases.
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.
Many engineers wish to deploy modern neural networks in memory-limited settings; but the development of flexible methods for reducing memory use is in its infancy, and there is little knowledge of the resulting cost-benefit. We propose structural model distillation for memory reduction using a strategy that produces a …
A new method reduces memory usage in neural networks by 36-81%.
problem Minimizing memory usage in neural networks during backpropagation.
method Formalized as a graph theory problem, uses dynamic programming to minimize computational overhead.
result Reduces peak memory consumption by 36-81% on various networks.
Global convergence of an online (stochastic) limited memory version of the Broyden-Fletcher- Goldfarb-Shanno (BFGS) quasi-Newton method for solving optimization problems with stochastic objectives that arise in large scale machine learning is established. Lower and upper bounds on the Hessian eigenvalues of the sample …
SliceOut speeds up deep learning training without sacrificing accuracy.
problem Frequent model re-training and large model training workloads in deep learning.
method SliceOut uses dropout-inspired scheme to drop contiguous sets of units at random, leveraging GPU memory layout.
result 10-40% speedups and memory reduction with minimal accuracy loss.
Enhanced Hopfield model boosts memory retrieval capacity.
problem Memory retrieval in modern Hopfield models with limited capacity.
method Introduces a learnable feature map transforming energy function into kernel space, minimizing separation loss for uniform memory distribution.
result Significant reduction in metastable states, enhancing memory capacity and retrieval accuracy.
Improved biclustering algorithm reduces memory usage and runtime.
problem Efficiently enumerating maximal biclusters in numerical datasets.
method Online partitioning to guide biclustering results.
result RIn-Close_CVC3 reduces memory usage and runtime, handles missing values.
4-bit quantization reduces U-Net memory by 8x with minimal accuracy loss.
problem Reducing memory and computation time in deep learning models.
method Fixed-point quantization of U-Net architecture.
result 8x reduction in memory usage with minimal accuracy loss.
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 method to reduce memory usage in NAS by pruning the search space.
problem High GPU memory consumption in One-Shot NAS techniques.
method Utilising Zero-Shot NAS to prune the search space before applying One-Shot NAS.
result Reduces memory consumption by 81% while maintaining accuracy.
Paper proposes efficient BNN inference flow to reduce computation and memory costs.
problem High computation complexity in Bayesian Neural Networks (BNNs) limits deployment in power-constrained systems.
method Feature decomposition and memorization strategy to reduce computations and a memory-friendly computing framework to reduce memory overhead.
result Reduces computation by about half and energy consumption by 73% with 14% area overhead.
SDA method reduces memory and time for assimilating noisy geophysical data.
problem Challenges in identifying state trajectories of high-dimensional geophysical systems.
method Score-based data assimilation with modified score network architecture.
result Promising results for a two-layer quasi-geostrophic model.
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.
A new text classification method using separable convolution reduces memory consumption.
problem Manual categorization of documents is inefficient and resource-intensive.
method Introducing a new architecture based on separable convolution for text classification.
result Achieved a drastic reduction in trainable parameters without compromising accuracy.
DRLViz interprets deep RL agent memory for better understanding.
problem Understanding complex deep RL agent memory.
method Visual analytics interface to reduce and interpret memory vectors.
result Experts can better understand and investigate agent decisions.
This research uncovers high-performing subnetworks in deep GNNs without training.
problem Challenges in applying SLTH to deeper GNNs with high memory requirements.
method Introduces Multicoated Supermasks (M-Sup) and Multi-Stage Folding for GNNs.
result Uncovered untrained recurrent networks with performance similar to trained models.
KineticSim accelerates financial market simulations 3406x over CPU.
problem Simulating financial markets at scale with multi-agent models is bottlenecked by sequential processing and GPU kernel overhead.
method Formalized and implemented a reusable parallel design pattern for iterative multi-agent reductions in thread-block shared memory.
result Achieved a peak throughput of over 54.7 billion agent-events per second, delivering 3406x speedup over CPU.
Reversible RNNs reduce memory usage in training without sacrificing performance.
problem Memory-intensive training of RNNs limits model flexibility.
method Developed a scheme for perfect reversible RNNs with forgetting, reducing memory by 10-15x.
result Achieved comparable performance to traditional models with reduced activation memory cost.
Eye tracking measures ADHD-related working memory deficits.
problem Diagnosing ADHD in adults requires reliable measures of working memory capacity.
method Eye tracking technology and machine learning applied to a working memory task.
result Machine learning generated features unique to ADHD.
New method reduces memory usage in deep HRNNs by replacing gradient backpropagation with local losses.
problem Memory constraints in training deep hierarchical RNNs.
method Replace gradient backpropagation with locally computable losses in deep HRNNs.
result Memory requirements reduced by a factor exponential in hierarchy depth.
Serenity optimizes neural network execution for edge devices by scheduling with optimal memory footprint.
problem Order of nodes in irregular neural networks affects memory footprint, complicating execution under resource constraints.
method Memory-aware compiler using dynamic programming and graph rewriting to find optimal schedules.
result Achieves optimal peak memory and further improves it with graph rewriting, reducing memory usage by 1.68x-1.86x compared to TensorFlow Lite.
BatchEnsemble reduces ensemble costs by 3X in training and testing.
problem High costs for training and testing ensembles of neural networks.
method Defines each weight matrix as a Hadamard product of a shared matrix and a rank-one matrix per member.
result Achieves 3X speedup and 3X memory reduction in test time for ensembles of size 4.
New algorithm learns optimal policies with minimal memory and time.
problem Learning optimal policies in discounted MDPs with short burn-in time.
method Variance reduction and adaptive policy switching.
result First regret-optimal model-free algorithm with low burn-in time.
This paper reviews methods to create compact neural networks for IoT applications.
problem Complex deep neural networks are costly and slow, hindering real-world deployment.
method Automatic synthesis of compact, accurate DNN/LSTM models.
result Compact neural networks reduce energy consumption, memory, and inference time.
In this paper we study a family of variance reduction methods with randomized batch size---at each step, the algorithm first randomly chooses the batch size and then selects a batch of samples to conduct a variance-reduced stochastic update. We give the linear convergence rate for this framework for composite functions…
A new method reduces memory usage for deep neural networks ensembles.
problem Reducing memory footprint of ensemble methods for deep learning.
method Extract multiple sub-networks from a single neural network through end-to-end optimization.
result Achieves higher or comparable accuracy with significantly less memory usage.
New method for multi-modal depth prediction challenges.
problem Challenges in applying unimodal coreset selection to multi-modal data.
method Adapted state-of-the-art coreset selection technique for multimodal data.
result Challenges in extending unimodal algorithms to multi-modal scenarios.
A new framework for efficient sequence maps using Bayesian filtering and covariance.
problem Designing efficient recurrent sequence maps from explicit memory assumptions.
method Design-model framework, exact Bayesian filtering, query-dependent readout, linear-Gaussian instantiation.
result Improved robustness and retrieval performance across various benchmarks.
Reduced-gate LSTM improves spatiotemporal prediction with less parameters.
problem Next-frame video prediction in deep learning.
method Predictive coding framework with reduced-gate convolutional LSTM.
result Reduced-gate model achieves equal or better accuracy with fewer parameters.
New algorithms provide long-term memory guarantees for online learning.
problem Achieving long-term memory in online learning for experts and bandits.
method Reduction to typical switching regret, developing various algorithms with specific regret bounds.
result Developed algorithms with a new regret bound of O ( T ( S ln T + n ln K ) ) \mathcal{O}(\sqrt{T(S\ln T + n \ln K)}) O ( T ( S ln T + n ln K ) ) . Variance reduction has been commonly used in stochastic optimization. It relies crucially on the assumption that the data set is finite. However, when the data are imputed with random noise as in data augmentation, the perturbed data set be- comes essentially infinite. Recently, the stochastic MISO (S-MISO) algorithm i…
Efficient FPGA dropout algorithm reduces memory usage.
problem Overfitting in deep neural networks.
method Hardware-oriented dropout algorithm for FPGA implementation.
result Significant resource reduction in FPGA implementation.
RIn-Close_CVC2 improves biclustering efficiency by reducing memory usage.
problem Mining maximal biclusters in numerical datasets efficiently and without redundancy.
method Proposes RIn-Close_CVC2, a new version of RIn-Close_CVC that eliminates redundant biclusters without a symbol table.
result RIn-Close_CVC2 reduces memory usage and improves runtime compared to RIn-Close_CVC.
Sparse Transformers reduce memory and time requirements for long sequence modeling.
problem Quadratic growth in memory and time with transformer sequence length.
method Sparse factorizations of attention matrix, deeper network training, attention matrix recomputation, fast attention kernels.
result Sparse Transformers can model sequences up to tens of thousands of timesteps with hundreds of layers.
We present CYCLADES, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting. CYCLADES is asynchronous during shared model updates, and requires no memory locking mechanisms, similar to HOGWILD!-type algorithms. Unlike HOGWILD!, CYCLADES introduces no conflicts during the par…
Variance reduction (VR) methods boost the performance of stochastic gradient descent (SGD) by enabling the use of larger, constant stepsizes and preserving linear convergence rates. However, current variance reduced SGD methods require either high memory usage or an exact gradient computation (using the entire dataset)…
Recent progress in deep learning is revolutionizing the healthcare domain including providing solutions to medication recommendations, especially recommending medication combination for patients with complex health conditions. Existing approaches either do not customize based on patient health history, or ignore existi…
EnLSTM network improves log generation from small datasets.
problem Generating well logs from small datasets with high accuracy.
method Combining ENN and C-LSTM networks with perturbation methods.
result 34% reduction in mean-square-error compared to existing models.
Improves energy efficiency of neuromorphic hardware by optimizing memory organization and encoding schemes.
problem Energy inefficiency in neuromorphic hardware, especially in digital accelerators.
method Synthesized controller and memory for different encoding schemes, introduced functional encoding for structured connectivity.
result Functional encoding offers a 58% reduction in energy for weight updates in convolutional layers.