RER improves sample complexity by updating in reverse order.
problem Theoretical analysis limits RER's convergence rate.
method Tighter analysis for larger learning rates and longer sequences.
result RER converges faster with larger learning rates and longer sequences.
Current recommender systems exploit user and item similarities by collaborative filtering. Some advanced methods also consider the temporal evolution of item ratings as a global background process. However, all prior methods disregard the individual evolution of a user's experience level and how this is expressed in th…
The paper analyzes and improves the learning rates of distributed kernel ridge regression.
problem Generalization performance and learning rates of distributed kernel ridge regression.
method The paper derives optimal learning rates for DKRR in expectation and probability, proposes a communication strategy to improve learning performance, and evaluates these through theory and experiments.
result The communication strategy significantly improves the learning performance of DKRR, as demonstrated by both theoretical assessments and numerical experiments.
Paper proposes a surrogate model for efficient experience rating in large insurance portfolios.
problem Inexpensive and transparent computation of Bayesian premiums for large insurance portfolios.
method Surrogate modeling approach using likelihood-based summary statistics.
result Reduced computational burden and provided a transparent way of computing Bayesian premiums.
Approximates bond option volatilities using affine short-rate models.
problem Calculating implied volatilities for bond options.
method Derive asymptotic approximation for bond option volatilities under affine short-rate dynamics.
result Accuracy of approximation validated through numerical experiments.
Paper improves learning rates for SGD and NAG.
problem Generalization performance of stochastic optimization algorithms.
method Establishes new learning rates for SGD and NAG.
result Improved guarantees in some settings or comparable rates under weaker assumptions.
Recommendation systems and computing advertisements have gradually entered the field of academic research from the field of commercial applications. Click-through rate prediction is one of the core research issues because the prediction accuracy affects the user experience and the revenue of merchants and platforms. Fe…
T-Rex selector selects variables fast and controls FDR in high-dimensional data.
problem Variable selection in high-dimensional data with FDR control.
method Fused solutions of early terminated random experiments.
result FDR control at target level with high variable selection power.
Developed unbiased estimators for Heston model with stochastic interest rates.
problem Estimating the Heston model with stochastic interest rates.
method Combined unbiased estimators with the Heston model and developed a semi-exact log-Euler scheme.
result Convergence rate of O(h) in the L2 norm for a wide range of models. The paper improves evolutionary computation by optimizing selection rates.
problem Choosing the right selection rate in evolutionary computation.
method The paper proves mathematically that a selection rate of μ/λ leads to better progress rates and provides a theoretical basis for this.
result The theoretical selection rate μ/λ leads to a better progress rate of order O(λ^-1) compared to O(λ^-2/d).
SALR improves deep learning generalization by dynamically adjusting learning rates.
problem Improving generalization in deep learning models.
method Sharpness-aware learning rate scheduling based on local loss function sharpness.
result SALR drives solutions to flatter regions, improving generalization and convergence.
D-Adaptation automatically sets optimal learning rates without manual tuning.
problem Optimizing learning rates for efficient convergence in machine learning.
method D-Adaptation, which asymptotically achieves optimal learning rates without back-tracking or additional evaluations.
result D-Adaptation automatically matches hand-tuned learning rates across diverse problems.
We prove optimal bounds for the convergence rate of ordinal embedding (also known as non-metric multidimensional scaling) in the 1-dimensional case. The examples witnessing optimality of our bounds arise from a result in additive number theory on sets of integers with no three-term arithmetic progressions. We also carr…
This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied in this paper is the learning rate. MI between the output layer and true outcomes is used to dynamically set the learning rate of the network through the trainin…
Sparse PCA selects variables with FDR control for improved performance.
problem Sparse PCA selects irrelevant variables when maximizing explained variance.
method Proposes FDR-controlled selection using T-Rex selector.
result Significant performance improvement over traditional sparse PCA.
Cyclical learning rates improve DRL performance without manual tuning.
problem Manual hyperparameter tuning in DRL is time-consuming and error-prone.
method Proposes cyclical learning rates for DRL problems.
result Cyclical learning achieves similar or better results than fixed learning rates.
This paper introduces a Bayesian framework for optimizing online experiments to maximize profit.
problem Statistical flaws and reliance on proxy metrics in A/B tests compromise their effectiveness.
method Hierarchical Bayesian model for estimating conversion probability and monetary value, decision-theoretic stopping rule.
result The framework ensures experiments conclude when no variant offers a significant profit improvement, conserving resources.
Large learning rates improve generalization, but optimal ranges are narrower than previously thought.
problem Optimizing learning rates for neural network training.
method Detailed exploration of learning rate ranges in a simplified setup, validating findings in a practical setting.
result Optimal learning rate ranges are significantly narrower than previously assumed.
Mixed likelihood GPs improve model performance in human-in-the-loop experiments.
problem Lack of auxiliary information in traditional GPs for human responses.
method Propose mixed likelihood variational GPs to leverage auxiliary information.
result Modeling performance improvements across diverse applications.
The paper analyzes insurance risks using stochastic models.
problem Interest rate and variance risks in unit-linked insurance policies.
method General stochastic volatility models and stochastic interest rates are used to price unit-linked life insurance contracts.
result A perfect hedging strategy is provided and compared with the Black-Scholes model.
We propose a new model for pricing Quanto CDS and risky bonds. The model operates with four stochastic factors, namely: hazard rate, foreign exchange rate, domestic interest rate, and foreign interest rate, and also allows for jumps-at-default in the FX and foreign interest rates. Corresponding systems of PDEs are deri…
nGPT learns to transfer learning rates across model dimensions and token horizons.
problem nGPT does not transfer learning rates across model size and token horizon.
method Combining numerical experiments with alignment exponents, a novel nGPT parameterization νGPT is developed.
result νGPT exhibits learning rate transfer across width, depth, and token horizon.
Paper generalizes extragradient methods for solving equations and inclusions with improved convergence rates.
problem Solving equations and inclusions using extragradient methods.
method Unified and generalized extragradient methods for a broader class of algorithms, analyzing sublinear convergence rates.
result Unified and improved convergence results for various extragradient variants.
Random learning rate improves neural network training without extra cost.
problem Optimizing neural networks with stochastic gradient descent.
method Uniformly-distributed random learning rate in SGD.
result Random learning rate yields better regularization without extra computational cost.
Fractal learning rate schedules accelerate vanilla gradient descent.
problem Difficulty in tuning learning rates in iterative optimization.
method Introduce Chebyshev learning rate schedule for gradient descent.
result Locally unstable updates can lead to convergence in deep learning.
The study proposes algorithms to minimize rating discordance in missing data.
problem Missing ratings in combined rating lists.
method Optimization models and algorithms that minimize total rating discordance.
result The proposed methods outperform state-of-the-art imputation methods in accuracy.
GradaGrad adapts learning rate non-monotonically, overcoming AdaGrad's step size decrease.
problem Fixed learning rate in AdaGrad leads to step size decrease over time.
method Introduces GradaGrad, which grows or shrinks the learning rate based on a different accumulation in the denominator.
result GradaGrad achieves similar convergence rates as AdaGrad and demonstrates non-monotone adaptation.
SALSA automatically adjusts learning rates in stochastic gradient methods.
problem Automatic adjustment of learning rates in stochastic gradient methods.
method SALSA uses a line-search procedure to gradually increase the learning rate, then a statistical test to decrease it.
result SALSA matches the performance of best hand-tuned learning rate schedules in deep learning tasks.
Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate. The sensitivity to the learning rate is due to the reliance on backpropagation to train the network. In this paper we present the first application of Implicit Stochastic Gradient Descent (ISGD) to…
This paper studies the complexity of the stochastic gradient algorithm for PCA when the data are observed in a streaming setting. We also propose an online approach for selecting the learning rate. Simulation experiments confirm the practical relevance of the plain stochastic gradient approach and that drastic improvem…
We study two time-scale linear stochastic approximation algorithms, which can be used to model well-known reinforcement learning algorithms such as GTD, GTD2, and TDC. We present finite-time performance bounds for the case where the learning rate is fixed. The key idea in obtaining these bounds is to use a Lyapunov fun…
Optimizing deep neural networks is largely thought to be an empirical process, requiring manual tuning of several hyper-parameters, such as learning rate, weight decay, and dropout rate. Arguably, the learning rate is the most important of these to tune, and this has gained more attention in recent works. In this paper…
The learning rate is one of the most important hyper-parameters for model training and generalization. However, current hand-designed parametric learning rate schedules offer limited flexibility and the predefined schedule may not match the training dynamics of high dimensional and non-convex optimization problems. In …
AutoGD automatically adjusts learning rates for gradient descent.
problem Optimizing learning rates for gradient descent methods.
method AutoGD automatically adjusts learning rates based on iteration.
result AutoGD can recover the optimal rate of GD for a broad class of functions.
Cyclical learning rate improves neural machine translation performance.
problem Optimizing learning rate for neural machine translation.
method Applied cyclical learning rate to transformer-based neural networks.
result Cyclical learning rate significantly impacts neural machine translation performance.
We present a novel method for the numerical pricing of American options based on Monte Carlo simulation and the optimization of exercise strategies. Previous solutions to this problem either explicitly or implicitly determine so-called optimal exercise regions, which consist of points in time and space at which a given…
Attribute-aware CF models aims at rating prediction given not only the historical rating from users to items, but also the information associated with users (e.g. age), items (e.g. price), or even ratings (e.g. rating time). This paper surveys works in the past decade developing attribute-aware CF systems, and discover…
We present a general framework for solving a large class of learning problems with non-linear functions of classification rates. This includes problems where one wishes to optimize a non-decomposable performance metric such as the F-measure or G-mean, and constrained training problems where the classifier needs to sati…
Study proves convergence of interest rate model approximations.
problem Investigating convergence of stochastic interest rate models.
method Developed analytical tools for true and truncated EM solutions, proving convergence in probability.
result True solution converges in probability to truncated EM solution as step size approaches zero.
We improve private training accuracy with learning rate schedules and matrix factorizations.
problem Private training with learning rate schedules and correlated noise.
method General upper and lower bounds for learning rate schedules, memory-efficient constructions, and schedule-aware factorizations.
result Schedule-aware factorizations improve accuracy in private training.
New methods for inferring, predicting, and estimating continuous-time, discrete-event processes.
problem Inferring, predicting, and estimating entropy rate of continuous-time, discrete-event processes.
method Bayesian structural inference extended with neural networks.
result Methods are competitive for prediction and entropy-rate estimation with state-of-the-art.
Adaptive-SGD method optimizes machine learning training with dynamic batch and step sizes.
problem Optimizing machine learning training with adaptive batch and step sizes.
method Adaptive-SGD method that dynamically adjusts batch size and step size based on local curvature and probability of descent directions.
result Adaptive-SGD achieves global linear convergence on self-concordant functions and compares favorably to fine-tuned methods.
Hamiltonian Monte Carlo on ReLU networks is inefficient due to large local error.
problem Inefficiency of Hamiltonian Monte Carlo on ReLU neural networks.
method Analysis of Hamiltonian Monte Carlo with leapfrog integrator for Bayesian neural network inference.
result Leapfrog HMC for ReLU networks has a large local error rate of Ω(ε), leading to inefficiency. Common event-triggered state estimation (ETSE) algorithms save communication in networked control systems by predicting agents' behavior, and transmitting updates only when the predictions deviate significantly. The effectiveness in reducing communication thus heavily depends on the quality of the dynamics models used …
This paper reviews methods for constructing confidence intervals for error rates in 1:1 matching tasks.
problem Challenges in assessing uncertainty of error rates in matching algorithms, especially when data are dependent and error rates are low.
method Derives and examines statistical properties of methods for constructing confidence intervals for error rates in 1:1 matching tasks.
result Coverage and interval width vary with sample size, error rates, and data dependence.
We consider rate swaps which pay a fixed rate against a floating rate in presence of bid-ask spread costs. Even for simple models of bid-ask spread costs, there is no explicit strategy optimizing an expected function of the hedging error. We here propose an efficient algorithm based on the stochastic gradient method to…
Stochastic gradient descent with a large initial learning rate is widely used for training modern neural net architectures. Although a small initial learning rate allows for faster training and better test performance initially, the large learning rate achieves better generalization soon after the learning rate is anne…
Proposes new listwise learning-to-rank models to address rating ties and document relevance.
problem Rating ties and document relevance in existing listwise learning-to-rank models.
method Models ranking as selecting documents from a candidate set based on unique rating levels. Uses a new loss function and adapted RNN model for refining prediction scores.
result Models notably outperform state-of-the-art learning-to-rank models on four public datasets.