Accelerates Riemannian gradient methods with extrapolation.
problem Optimizing functions on manifolds efficiently.
method Extrapolating iterates in Riemannian gradient descent.
result Achieves optimal convergence rate and computational advantage.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “acceleration strategies”
We revisit the stochastic limited-memory BFGS (L-BFGS) algorithm. By proposing a new framework for the convergence analysis, we prove improved convergence rates and computational complexities of the stochastic L-BFGS algorithms compared to previous works. In addition, we propose several practical acceleration strategie…
Survey on pruning CNN models to reduce size for edge devices.
problem Reducing large CNN models for edge deployment.
method Comprehensive review of pruning strategies, criteria, and techniques.
result Pruning accelerates CNN models for edge applications.
Adaptive Nesterov Accelerated Distributional Deep Hedging for Efficient Volatility Risk Managementcs.LG
ANADDH uses deep learning to improve volatility risk management.
problem Traditional Vega hedging strategies are inadequate for rapidly changing markets.
method Combines distributional reinforcement learning with adaptive Nesterov acceleration.
result Significant performance gains over existing hedging techniques.
Accelerating Non-Negative and Bounded-Variable Linear Regression Algorithms with Safe Screeningcs.LG
The paper accelerates regression algorithms by identifying saturated coordinates.
problem Non-negative and bounded-variable linear regression problems.
method Safe screening technique to identify saturated coordinates.
result The approach provides theoretical guarantees for identifying saturated coordinates.
Paper proposes a new framework for combining investment strategies without market-specific assumptions.
problem Lack of a distribution-free and consistent preference framework for decision-making in combining investment strategies.
method Introduces a novel framework for decision-making in combining strategies, free from market conditions and statistical assumptions.
result Proposed strategies outperform individual component strategies in long-term wealth accumulation, with small tradeoffs in Sharpe ratios.
New accelerators for EM improve convergence speed in complex mixture models.
problem Improving the convergence speed of the EM algorithm for complex mixture models.
method Derive a new operator connecting global descent and local convergence, and use it to develop two acceleration strategies.
result Two new acceleration strategies (G-Accelerator and Geo-Adaptive) significantly improve EM algorithm performance.
Accelerates optimal transport computation by 10x with spectral insights.
problem Exponential slow-down of convergence in Entropic Optimal Transport as regularization weakens.
method Spectral insights and spectral warm-start strategy to mitigate convergence issues.
result Faster convergence compared to the reference method Sinkhorn algorithm.
In this article, we consider the optimal execution problem associated to accelerated share repurchase contracts. When firms want to repurchase their own shares, they often enter such a contract with a bank. The bank buys the shares for the firm and is paid the average market price over the execution period, the length …
New method accelerates Bayesian imaging using Langevin sampling.
problem Bayesian inference in imaging inverse problems with convex geometry.
method Stochastic relaxed proximal-point iteration targeting posterior distribution.
result Accelerated convergence for -strongly log-concave targets.
We propose a novel method to accelerate Lloyd's algorithm for K-Means clustering. Unlike previous acceleration approaches that reduce computational cost per iterations or improve initialization, our approach is focused on reducing the number of iterations required for convergence. This is achieved by treating the assig…
This paper is concerned with improving the empirical convergence speed of block-coordinate descent algorithms for approximate nonnegative tensor factorization (NTF). We propose an extrapolation strategy in-between block updates, referred to as heuristic extrapolation with restarts (HER). HER significantly accelerates t…
New algorithms accelerate model-based optimization for stochastic problems.
problem Optimizing model-based stochastic optimization problems efficiently.
method Proposed new model-based algorithms with acceleration and minibatch techniques.
result Non-asymptotic convergence guarantees with linear speedup in minibatch size.
We introduce a generic scheme for accelerating gradient-based optimization methods in the sense of Nesterov. The approach, called Catalyst, builds upon the inexact accelerated proximal point algorithm for minimizing a convex objective function, and consists of approximately solving a sequence of well-chosen auxiliary p…
This review article surveys data augmentation MCMC algorithms.
problem Sampling from intractable probability distributions.
method Comprehensive study of DA MCMC algorithms, their convergence properties, and acceleration strategies.
result Synthesizes recent developments and provides insights for researchers.
Inference of latent feature models in the Bayesian nonparametric setting is generally difficult, especially in high dimensional settings, because it usually requires proposing features from some prior distribution. In special cases, where the integration is tractable, we can sample new feature assignments according to …
Seesaw optimizes training by balancing learning rate and batch size, accelerating model pretraining.
problem Optimizing training efficiency for large language models with adaptive optimizers.
method Develops a principled framework for batch-size scheduling, introducing Seesaw which multiplies learning rate by 1/√2 and doubles batch size.
result Empirically, Seesaw reduces wall-clock time by approximately 36% compared to cosine decay, matching theoretical limits.
Paper proposes a new binary quantization method for faster DNN inference.
problem Accelerating deep neural network inference on resource-limited devices.
method Quantized Compressed Sensing (QCS) for binary quantization.
result The proposed method preserves benefits of standard methods while reducing quantization error.
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.
Model-free deep reinforcement learning (RL) algorithms have been widely used for a range of complex control tasks. However, slow convergence and sample inefficiency remain challenging problems in RL, especially when handling continuous and high-dimensional state spaces. To tackle this problem, we propose a general acce…
We present a new framework for Hermite fractional financial markets, generalizing the fractional Brownian motion and fractional Rosenblatt markets. Considering pure and mixed Hermite markets, we introduce a strategy-specific arbitrage tax on the rate of transaction volume acceleration of the hedging portfolio as the pr…
Recently, there has been great interest in connections between continuous-time dynamical systems and optimization methods, notably in the context of accelerated methods for smooth and unconstrained problems. In this paper we extend this perspective to nonsmooth and constrained problems by obtaining differential inclusi…
SuNCEt accelerates contrastive learning with minimal labeled data.
problem Efficiently learning visual representations with limited labeled data.
method Noise-contrastive estimation and neighbourhood component analysis-based semi-supervised loss.
result SuNCEt achieves semi-supervised learning accuracy with less than half the labeled data.
New algorithms accelerate solving nonlinear matrix decomposition with ReLU.
problem Nonlinear matrix decomposition with ReLU function.
method Two new algorithms: A-NMD and 3B-NMD, with adaptive extrapolation and block parametrization.
result Effective algorithms accelerate solving ReLU-NMD problems.
SparseRT accelerates sparse computations on GPUs for deep learning inference.
problem Efficiently handling unstructured sparsity patterns on GPUs for deep learning.
method SparseRT, a code generator that leverages unstructured sparsity for accelerating sparse linear algebra operations.
result Geometric mean speedups of 3.4x at 90% sparsity and 5.4x at 95% sparsity for 1x1 convolutions and fully connected layers.
Deriving conditional and marginal distributions using conjugacy relationships can be time consuming and error prone. In this paper, we propose a strategy for automating such derivations. Unlike previous systems which focus on relationships between pairs of random variables, our system (which we call Autoconj) operates …
Improves learning of spectral mixture kernels with approximate Bayesian inference.
problem Difficult optimization of large number of SM kernel parameters.
method Approximate Bayesian inference using variational distribution of spectral points and random Fourier features.
result Accelerates convergence and leads to better optimal parameters.
The past several years have seen both an explosion in the use of Convolutional Neural Networks (CNNs) and the design of accelerators to make CNN inference practical. In the architecture community, the lion share of effort has targeted CNN inference for image recognition. The closely related problem of video recognition…
In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. More precisely, we interpret a large class of stochastic optimization methods as procedures that iteratively minimize a surrogate of th…
A new ES method improves reinforcement learning speed and accuracy.
problem Slow convergence and local maxima in reinforcement learning.
method Directional Gaussian Smoothing Evolution Strategy (DGS-ES)
result DGS-ES accelerates RL training with high accuracy and nonlocal search direction.
In unsupervised learning, an unbiased uniform sampling strategy is typically used, in order that the learned features faithfully encode the statistical structure of the training data. In this work, we explore whether active example selection strategies - algorithms that select which examples to use, based on the curren…
Accelerates convergence in global non-convex optimization with reversible diffusion.
problem Global non-convex optimization challenges.
method Utilizes reversible diffusion processes with adaptive diffusion coefficients.
result Accelerated convergence with reduced discretization error.
Study reviews tree-based methods and introduces new ensemble strategies.
problem Improving the efficiency and performance of tree-based machine learning models.
method Review of tree-based methods, introduction of ISLE framework, ARM model combination strategy, and modified ISLEs.
result Performance evaluation of modified ISLEs on real data sets.
First-order optimization methods, such as stochastic gradient descent (SGD) and its variants, are widely used in machine learning applications due to their simplicity and low per-iteration costs. However, they often require larger numbers of iterations, with associated communication costs in distributed environments. I…
Paper finds sharpness differences in transformer blocks accelerating LLM training.
problem Understanding and accelerating large language model pre-training.
method Uncovering sharpness disparity across transformer blocks and proposing Blockwise Learning Rate.
result Blockwise Learning Rate strategy accelerates LLM pre-training with lower loss and speedup.
A deep learning strategy outperforms traditional methods in stocks portfolio management.
problem Optimizing stock portfolio performance using machine learning.
method Deep Deterministic Policy Gradient framework with neural networks.
result Compound annual return rate of 14.12% compared to 7 other strategies.
Consider a two-player zero-sum stochastic game where the transition function can be embedded in a given feature space. We propose a two-player Q-learning algorithm for approximating the Nash equilibrium strategy via sampling. The algorithm is shown to find an -optimal strategy using sample size linear to the number …
We formalize the problem of trading-off DNN training time and memory requirements as the tensor rematerialization optimization problem, a generalization of prior checkpointing strategies. We introduce Checkmate, a system that solves for optimal rematerialization schedules in reasonable times (under an hour) using off-t…
Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has proved to be an effective strategy for reducing the number of interactions required to train a policy. Online imitation learning, which inter…
Fundamental Framework for Technical Analysiscond-mat.stat-mech
Starting from the characterization of the past time evolution of market prices in terms of two fundamental indicators, price velocity and price acceleration, we construct a general classification of the possible patterns characterizing the deviation or defects from the random walk market state and its time-translationa…
New method accelerates optimization in fixed time, improving convergence rates.
problem Optimization in large-scale data-driven problems.
method Gradient-based optimization framework with fixed-time stable dynamical systems.
result Achieves convergence to the optimizer in a fixed number of iterations, independent of initialization.
A global consumer-led strategy to tackle climate changephysics.soc-ph
A successful response to climate change needs vast investments in low-carbon research, energy, and sustainable development. Governments can drive research, provide environmental regulation, and accelerate global development, but the necessary low-carbon investments of 2-3% GDP have yet to materialise. A new strategy to…
Often times, in many design problems, there is a need to select a small set of informative or representative elements from a large ground set of entities in an optimal fashion. Submodular optimization that provides for a formal way to solve such problems, has recently received significant attention from the controls co…
Boosted Frank-Wolfe accelerates optimization for nonconvex problems.
problem Optimizing nonconvex and quasar-convex objectives efficiently.
method Developed a novel step size strategy for stochastic Frank-Wolfe, extending it to various gradient estimators.
result Boosted Frank-Wolfe achieves faster convergence rates than non-boosted Frank-Wolfe.
NIFTy.re accelerates imaging models and expands Gaussian processes and variational inference.
problem Slow performance and limited inference strategies in NIFTy.
method Rewritten NIFTy with new modeling principles, inference strategies, and JAX integration.
result Dramatic acceleration of models and new inference capabilities.
FinRL-Podracer: High Performance and Scalable Deep Reinforcement Learning for Quantitative Financeq-fin.CP
FinRL-Podracer accelerates DRL trading strategies in finance with high performance and scalability.
problem Challenges in applying deep reinforcement learning to finance trading models.
method Proposes an RLOps framework and high-performance cloud solution for DRL trading.
result FinRL-Podracer outperforms existing DRL libraries by 12-35% in annual return, 0.1-0.6 in Sharpe ratio, and 3-7 times in training time.
cuRegOT accelerates GPU-based entropic OT solving.
problem Slow convergence and high computational cost of optimal transport on GPUs.
method High-performance GPU solver with algorithmic and architectural optimizations.
result Significant speedups over state-of-the-art solvers.
A faster EM algorithm for unsupervised Gaussian mixture models.
problem Efficiently determining the number of components in Gaussian mixture models.
method Adaptive Anderson Acceleration (AA) for EM algorithm, with novel monotonicity control and covariance matrix preservation.
result Significantly faster convergence compared to non-accelerated EM, up to 60X in some cases.