Meta-SAGE improves deep RL scalability for CO tasks by adapting pre-trained models to larger-scale problems.
problem Improving scalability of deep reinforcement learning models for combinatorial optimization tasks.
method Meta-SAGE combines a scale meta-learner and scheduled adaptation with guided exploration to adjust model parameters for larger-scale problems.
result Meta-SAGE outperforms previous methods and significantly improves scalability in CO tasks.
Unintended effects from scaling neural network outputs with adaptive learning rates.
problem Adaptive learning rate optimization's behavior is altered by output scaling, leading to misinterpretation.
method Presented a modified optimization algorithm to mitigate unintended effects.
result Adaptive learning rate's effectiveness is significantly impacted by output scaling, especially for small scaling factors.
This work bridges two views of feature learning in neural networks.
problem The relationship between kernel scale changes and data-adaptive feature learning in neural networks remains unresolved.
method Using statistical mechanics, the work derives analytical expressions for network output statistics across scaling regimes.
result Kernel adaptation can be reduced to an effective kernel rescaling, but multi-scale adaptive approach provides richer insights.
Locally adaptive clustering for tree delineation.
problem Tree delineation from distance data.
method Locally adaptive hierarchical cluster termination.
result Multi-scale alternative to conventional termination criteria.
TiAda adapts adaptive gradient methods for nonconvex minimax optimization.
problem Nonconvex minimax optimization challenges in achieving convergence.
method TiAda is a time-scale adaptive GDA algorithm for nonconvex minimax optimization.
result TiAda achieves near-optimal complexities in deterministic and stochastic settings.
ASAM improves deep neural network generalization by adapting sharpness to scale.
problem Fixed-radius sharpness measure is sensitive to parameter scaling, weakening its connection to generalization.
method Introduces adaptive sharpness, a scale-invariant measure, and proposes ASAM for deep learning.
result ASAM significantly improves model generalization performance across various datasets.
Recent advancements in recurrent neural network (RNN) research have demonstrated the superiority of utilizing multiscale structures in learning temporal representations of time series. Currently, most of multiscale RNNs use fixed scales, which do not comply with the nature of dynamical temporal patterns among sequences…
New bin-wise scaling methods improve prediction uncertainty calibration for machine learning.
problem Improving prediction uncertainty calibration for machine learning regression.
method Adaptations of Binwise Variance Scaling (BVS) with alternative loss functions and feature-based binning.
result Improved adaptivity and consistency in prediction uncertainty calibration.
CLAPS improves conformal regression by adaptively scaling interval widths based on last-layer Laplace uncertainty.
problem Lack of adaptive interval width scaling in conformal regression for heterogeneous inputs.
method CLAPS uses heteroscedastic last-layer Laplace uncertainty to adaptively scale interval widths, combining aleatoric and epistemic uncertainties.
result CLAPS provides competitive interval efficiency with nominal-level coverage, reducing to aleatoric scaling as epistemic uncertainty decreases.
The most widely used activation functions in current deep feed-forward neural networks are rectified linear units (ReLU), and many alternatives have been successfully applied, as well. However, none of the alternatives have managed to consistently outperform the rest and there is no unified theory connecting properties…
This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how does reward scaling affect non-saturating ReLU networks in RL? This question matters because ReLU is one of the most effective activation f…
New adaptive first-order methods improve on quasi-Newton variants.
problem Designing efficient gradient methods for practical applications.
method Online scaled gradient methods (OSGM) with new adaptive methods OSGM-Best.
result OSGM-Best matches quasi-Newton variants but requires less memory and cheaper iterations.
Optimizing full likelihoods adapts loss scales and shapes for robust modeling.
problem Rigid loss functions limit model adaptability and robustness.
method Optimize full likelihoods with adjustable parameters.
result Adaptive tuning of loss scales and shapes improves model robustness.
Neural HMM with AGA captures multi-scale dynamics in financial markets.
problem Capturing multi-scale temporal dynamics in financial markets.
method Parallel multi-resolution encoders, adaptive gating, and multi-head attention.
result Outperforms fixed-resolution baselines in predicting price movements and liquidity shocks.
For large scale on-line inference problems the update strategy is critical for performance. We derive an adaptive scan Gibbs sampler that optimizes the update frequency by selecting an optimum mini-batch size. We demonstrate performance of our adaptive batch-size Gibbs sampler by comparing it against the collapsed Gibb…
Skew-adaptive method improves prediction intervals for regression.
problem Improving prediction intervals for regression models, especially in cases of skewness and varying scales.
method Develops a skew-adaptive extension of split conformal prediction using an asymmetric interval family and gauge approach.
result Preserves marginal validity and adapts to local scale and skewness, with efficiency gains over existing methods.
New method trains deep networks robustly without adaptive methods.
problem Training deep networks with robustness and efficiency.
method Scale invariant architecture + SGD + weight decay + gradient clipping.
result SGD can achieve similar performance to adaptive methods like Adam.
Adaptive algorithms improve performance in non-convex optimization across various scenarios.
problem Improper handling of noise scales, gradient magnitudes, and smoothness in non-convex optimization.
method Design and analysis of noise-adaptive, scale-free, and generalized algorithms.
result Adaptive algorithms achieve optimal rates and performance in diverse optimization settings.
Most optimizers including stochastic gradient descent (SGD) and its adaptive gradient derivatives face the same problem where an effective learning rate during the training is vastly different. A learning rate scheduling, mostly tuned by hand, is usually employed in practice. In this paper, we propose CProp, a gradient…
Adaptive regularization prevents overfitting in large-scale sparse feature models.
problem Overfitting in models with large-scale sparse categorical features.
method Adaptive regularization of embedding layers' norm budget.
result Improves model performance within a single epoch and prevents multi-epoch performance degradation.
Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in existing GPUs. MPT is typically used in combination with a technique called los…
WALNUTS improves sampling efficiency and robustness for multi-scale distributions.
problem Adapting leapfrog step size for multi-scale posterior distributions.
method Adapts leapfrog step size at fixed intervals of simulated time, selecting the largest step size to keep energy error below a threshold.
result Substantial improvements in sampling efficiency and robustness compared to standard NUTS.
Most neural-network based speaker-adaptive acoustic models for speech synthesis can be categorized into either layer-based or input-code approaches. Although both approaches have their own pros and cons, most existing works on speaker adaptation focus on improving one or the other. In this paper, after we first systema…
Extends DRFGP to make GPs more robust and adaptive for dynamic, noisy data.
problem Limited scalability, static targets, and brittleness to outliers in GPs.
method Introduces robust-filtering update and dynamic adaptation mechanism.
result Enhanced stability and accuracy in modeling dynamic, noisy data.
Derives effective continuous dynamics for adaptive SGD methods.
problem Analyzing noise in adaptive SGD methods.
method Stochastic modified equations framework and Malladi's scaling rules.
result Sampling-induced noise in SGD limits to independent Brownian motions.
Online Platt Scaling adapts to varying data distributions.
problem Adapting Platt scaling to non-i.i.d. settings with distribution drift.
method Combines Platt scaling with online logistic regression and calibeating.
result OPS+calibeating method is guaranteed to be calibrated for adversarial outcomes.
New scalable methods for unbalanced optimal transport improve efficiency and applicability.
problem Scalable algorithms for unbalanced optimal transport remain underexplored.
method Analysis of semi-dual formulation and adaptive gradient methods.
result SGD methods achieve a convergence rate of O(n/εT) for large-scale applications.
Adapts to estimate functions from noisy ERT data.
problem Estimating functions from noisy Exponential Radon Transform data.
method Locally adaptive kernel type estimator for functions of varying smoothness.
result Achieves minimax optimal rate up to a log(n) factor for Sobolev functions.
AdAdaGrad optimizes batch sizes for deep learning models, reducing the generalization gap.
problem The generalization gap between large-batch and small-batch training in deep learning.
method AdAdaGrad introduces adaptive batch size strategies derived from adaptive sampling methods.
result AdAdaGradNorm converges to a first-order stationary point with a rate of O(1/K) in K iterations.
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.
EvoMSN tackles time series forecasting under distribution shifts by evolving multi-scale normalization.
problem Accurate long-term time series forecasting under complex distribution shifts.
method EvoMSN framework with multi-scale statistics prediction and adaptive ensembling for collaborative updating.
result Improves forecasting performance of five mainstream methods on benchmark datasets.
Optimal nonparametric regression estimator adapts to unknown smoothness.
problem Nonparametric regression with unknown smoothness.
method Constructs an interpolating estimator that adapts to unknown smoothness.
result Minimax optimal rates achieved on Hölder classes.
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.
Improved loss scaling for stochastic momentum algorithms in high dimensions.
problem Improving loss scaling for stochastic momentum algorithms in high dimensions.
method Dimension-adapted Nesterov acceleration (DANA) scales momentum hyperparameters based on model size and data complexity.
result DANA improves loss scaling exponents across various data and target complexities.
AdaScale SGD adapts learning rates for large-batch training efficiently.
problem Adapting learning rates for large-batch training to balance speed-ups and model quality.
method Adaptive learning rate adaptation based on gradient variance.
result AdaScale achieves reliable speed-ups for a wide range of batch sizes without degrading model quality.
New model for display advertising with stochastic and adversarial components.
problem Display advertising with stochastic and adversarial click-through-rates.
method Adversarial scaling model; two algorithms tested: action elimination and mirror descent.
result Two algorithms are robust to adversarial scaling.
New algorithms adapt to both gradient norms and comparator norms in online learning.
problem Adapting to both gradient norms and comparator norms in online learning.
method Developed parameter-free and scale-free algorithms for unbounded online convex optimization.
result Improved regret bounds for scale-invariant online prediction with linear models.
We introduce a framework to study the effective objectives at different time scales of financial market microstructure. The financial market can be regarded as a complex adaptive system, where purposeful agents collectively and simultaneously create and perceive their environment as they interact with it. It has been s…
DriftLite improves inference quality of diffusion models without retraining.
problem Adapting pre-trained diffusion models to new target distributions without retraining.
method Lightweight, training-free particle-based approach that steers inference dynamics with optimal stability control.
result Consistently reduces variance and improves sample quality over existing methods.
Preprocessing data is an important step before any data analysis. In this paper, we focus on one particular aspect, namely scaling or normalization. We analyze various scaling methods in common use and study their effects on different statistical learning models. We will propose a new two-stage scaling method. First, w…
EPC curriculum improves MARL performance as agent population grows.
problem Challenges in learning good policies for large multi-agent systems.
method Evolutionary Population Curriculum (EPC) for scaling MARL.
result EPC consistently outperforms baselines as agent population increases.
NUTS mixing time scales as d^(1/4) for Gaussian distributions.
problem Improving the efficiency of the No-U-Turn Sampler (NUTS) for Gaussian distributions.
method Coupling argument leveraging geometric structure of Gaussian concentration, uniformity analysis of NUTS transitions.
result The mixing time of NUTS scales as d^(1/4) for Gaussian distributions, up to logarithmic factors.
Optimization lies at the heart of machine learning and signal processing. Contemporary approaches based on the stochastic gradient method are non-adaptive in the sense that their implementation employs prescribed parameter values that need to be tuned for each application. This article summarizes recent research and mo…
New algorithm bounds MAB regret for unknown scale and magnitude of losses.
problem Adversarial Multi Armed Bandits with unknown scale and magnitude of losses.
method Design a bandit Follow The Regularized Leader (FTRL) algorithm with adaptive learning rate.
result First MAB bounds that adapt to L2 and L1 norms of losses. Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize. In this pap…
Optimal transport between Gaussian Mixture Models improves domain adaptation efficiency.
problem Adapting machine learning models to new data distributions with minimal access.
method Optimal transport between Gaussian Mixture Models (GMMs) for domain adaptation.
result Our methods are more efficient and scalable with sample size and dimensions.
ABS dynamically adjusts batch size based on policy stability, improving RL performance.
problem Diminishing returns with large batch sizes in RL due to non-stationary data.
method Adaptive Batch Scaling (ABS) with Behavioral Divergence metric.
result Larger batch sizes can improve RL performance, contrary to conventional wisdom.
The present contribution suggests the use of a multidimensional scaling (MDS) algorithm as a visualization tool for manifold-valued elements. A visualization tool of this kind is useful in signal processing and machine learning whenever learning/adaptation algorithms insist on high-dimensional parameter manifolds.