Adaptive SAA solves large-scale stochastic linear programs efficiently.
problem Solving large-scale two-stage stochastic linear programs.
method Iterative algorithm with adaptive sample size and warm starts.
result The algorithm converges to the true solution set with a probabilistic guarantee.
Paper introduces DOO models to outperform SAA out-of-sample.
problem Outperforming SAA in out-of-sample performance.
method Introduces DOO models that consider both worst-case and best-case scenarios.
result DOO models can always outperform SAA out-of-sample.
We introduce the SaaS Algorithm for semi-supervised learning, which uses learning speed during stochastic gradient descent in a deep neural network to measure the quality of an iterative estimate of the posterior probability of unknown labels. Training speed in supervised learning correlates strongly with the percentag…
The paper studies the convergence of SAA for systemic risk measures.
problem Theoretical convergence of SAA for set-valued systemic risk measures.
method General theory and specific case study with mixed-integer programming formulations.
result Theoretical convergence results for SAA under Wijsman and Hausdorff topologies.
The paper models SaaS products as insurance, offering new pricing tools.
problem Modeling capped-usage SaaS products with insurance principles.
method Frequency-severity decomposition, premium calculation, Monte Carlo simulations.
result SaaS pricing can be analyzed using insurance actuarial methods.
New research shows SAA can outperform SA for Wasserstein barycenters.
problem Optimizing Wasserstein barycenters with entropy regularization.
method Comparison of Stochastic Approximation (SA) and Sample Average Approximation (SAA) for large-scale problems.
result SAA can be more efficient than SA for Wasserstein barycenters, especially in large-scale settings.
Study integrates machine learning with SAA for optimizing decisions based on uncertain parameters and covariates.
problem Optimizing decisions under uncertain parameters and covariates.
method Data-driven frameworks integrating machine learning prediction models within SAA for scenario generation.
result Consistent and asymptotically optimal solutions under certain conditions, with finite sample guarantees.
Paper uses RNN to predict SaaS user lifetime value.
problem Predicting user lifetime value in SaaS applications.
method Recurrent Neural Network with multi-cell architecture, accounting for cohort, age-in-system, and contemporaneous information.
result Significantly improved prediction accuracy compared to existing models.
Although we have tons of machine learning tools to analyze data, most of them require users have some programming backgrounds. Here we introduce a SaaS application which allows users analyze their data without any coding and even without any knowledge of machine learning. Users can upload, train, predict and download t…
This study analyzes decision-making in diverse environments where past data may not predict future outcomes.
problem How to make decisions when past data is not indicative of future outcomes due to unobserved confounders.
method Developed a framework to analyze and bound the performance of data-driven policies in heterogeneous environments.
result Established a method to upper bound the asymptotic worst-case regret of policies and analyzed the performance of Sample Average Approximation (SAA).
SAA method solves insurance portfolio optimization with CVaR constraints.
problem Optimal allocation under CVaR constraint in insurance.
method Sample Average Approximation (SAA) method applied to CVaR constrained portfolio optimization.
result Convergence of SAA method and solution uniqueness proved under mild assumptions.
Novel approach simplifies VI problems with faster performance.
problem Black-box VI optimization problems.
method Sample Average Approximation (SAA) combined with quasi-Newton methods and line search.
result Achieves faster performance than existing methods.
New insights into bias-variance tradeoff for data-driven optimization under local misspecification.
problem Understanding the relative performance of SAA, IEO, and ETO under local misspecification.
method Developed a local misspecification perspective using contiguity theory in statistics.
result Explicit expressions for decision bias and geometric understanding of variance.
The study optimizes free trial lengths to boost subscriptions and consumer loyalty.
problem Optimizing free trial lengths to maximize customer acquisition and retention.
method A large-scale field experiment with personalized policy design and evaluation.
result Personalized free trial policies outperform uniform trial lengths.
The paper improves Monte Carlo methods for optimization problems.
problem Efficiently solving optimization problems with biased Monte Carlo estimators.
method Introduces Multilevel Monte Carlo (MLMC) within Sample Average Approximation (SAA).
result Establishes uniform convergence and sample complexity for MLMC in SAA.
New optimization method corrects data-driven optimizer's curse.
problem Over-optimistic evaluation in data-driven optimization.
method Smoothed f-Divergence Distributionally Robust Optimization (DRO). result Statistical bound on out-of-sample performance nearly tightest.
In this paper, we study a class of stochastic optimization problems, referred to as the \emph{Conditional Stochastic Optimization} (CSO), in the form of $\min_{x \in \mathcal{X}} \EE_ξf_ξ\Big({\EE_{η|ξ}[g_η(x,ξ)]}\Big)$, which finds a wide spectrum of applications including portfolio selection, reinforcement learning, …
A key factor in developing high performing machine learning models is the availability of sufficiently large datasets. This work is motivated by applications arising in Software as a Service (SaaS) companies where there exist numerous similar yet disjoint datasets from multiple client companies. To overcome the challen…
DADVI improves ADVI by using deterministic approximation for faster, more accurate posterior estimation.
problem Intractable posterior uncertainty estimates and lack of clear convergence criteria in ADVI.
method Replaces stochastic MFVB objective with deterministic Monte Carlo approximation (SAA) and uses second-order optimization.
result DADVI provides faster and more accurate posterior estimates with default settings.
The paper analyzes risk estimation methods and derives bounds for OCE risk.
problem Estimating the Optimized Certainty Equivalent (OCE) risk from samples.
method Derives mean-squared error and concentration bounds for SAA of OCE, and analyzes an efficient stochastic approximation-based estimator.
result Finite sample bounds and mis-identification probability bounds for the efficient estimator.
We develop a theory for valuing non-diversifiable mortality risk in an incomplete market. We do this by assuming that the company issuing a mortality-contingent claim requires compensation for this risk in the form of a pre-specified instantaneous Sharpe ratio. We apply our method to value life annuities. One result of…
We use a continuous version of the standard deviation premium principle for pricing in incomplete equity markets by assuming that the investor issuing an unhedgeable derivative security requires compensation for this risk in the form of a pre-specified instantaneous Sharpe ratio. First, we apply our method to price opt…
Personalizes query completion in digital commerce with image-based vectors.
problem High bounce rate and low recurring users in query completion.
method Injects dense vectors from product images into a noisy channel model.
result Image-based personalization improves query completion and user experience.
RL techniques improve radar spectrum sharing in crowded conditions.
problem Optimizing radar performance in congested spectrum environments.
method Comparison of RL algorithms including policy iteration and Deep RL.
result RL techniques outperform traditional SAA methods in radar spectrum sharing.
Optimizes shortfall risk using gradient-based methods.
problem Optimizing utility-based shortfall risk measures.
method Gradient-based stochastic optimization, non-asymptotic bounds derivation.
result Non-asymptotic convergence rate for optimizing UBSR.
We propose a novel supervised learning method to optimize the kernel in the maximum mean discrepancy generative adversarial networks (MMD GANs), and the kernel support vector machines (SVMs). Specifically, we characterize a distributionally robust optimization problem to compute a good distribution for the random featu…
Optimizes asset allocation with illiquid assets using MPC.
problem Strategic asset allocation with illiquid alternative asset classes.
method Formulates illiquid dynamics as a random linear system and proposes a convex optimization based MPC policy.
result Performance close to a fully liquid scenario, despite time delay and uncertainty.
The study improves Monte Carlo simulations for long-term investments using advanced financial models.
problem Improving the accuracy of long-term investment simulations.
method Developed a multivariate process incorporating recent financial models and probabilistic forecasts.
result Increased accuracy in predicting portfolio values over decades.
New findings show ETO outperforms IEO in well-specified models with sufficient data.
problem Comparing estimate-then-optimize (ETO) and integrated-estimation-optimization (IEO) methods in stochastic optimization.
method Analyzes the performance of ETO and IEO in well-specified and misspecified models using stochastic dominance.
result Simple ETO outperforms IEO asymptotically in well-specified models with sufficient data.
This paper tackles unpaired data in multi-view learning, proposing a new framework and models.
problem Handling unpaired data in multi-view learning, which is more common than paired data.
method Generalized uncorrelated multi-view subspace learning framework with successive alternating approximation (SAA) method.
result Proposed models perform competitively or better than baselines in multi-view feature extraction and multi-modality classification.
Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks. Despite their fast convergence, they can generalize worse than stochastic gradient descent. In this paper, by revisiting the design of Adagrad, we propose to split the network par…
Sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the-art performances while having clear advantages in terms of simplicity. However, comparisons are mostly done on speaker independent (SI) ASR systems, though speaker adapted conventional systems are commonly used in practice for improving robustness…
AdaPTS adapts univariate FMs for multivariate time series forecasting.
problem Challenges in managing feature dependencies and uncertainty quantification in multivariate time series forecasting.
method Adapters that transform multivariate inputs into a latent space and apply univariate FMs independently to each dimension.
result AdaPTS enhances forecasting accuracy and uncertainty quantification compared to baseline methods.
We propose a new concept named adaptive submodularity ratio to study the greedy policy for sequential decision making. While the greedy policy is known to perform well for a wide variety of adaptive stochastic optimization problems in practice, its theoretical properties have been analyzed only for a limited class of p…
Adaptive sequential decision making is one of the central challenges in machine learning and artificial intelligence. In such problems, the goal is to design an interactive policy that plans for an action to take, from a finite set of n actions, given some partial observations. It has been shown that in many applicat…
New algorithm reduces interventional strategy complexity for causal graph discovery.
problem Designing efficient interventional strategies for causal graph discovery.
method Developed an r-adaptive algorithm for causal graph discovery that minimizes the number of interventions.
result Achieved an approximation of O(min{r, log n} * n^{1/min{r, log n}}) for the verification number.
Automation of machine learning model development is increasingly becoming an established research area. While automated model selection and automated data pre-processing have been studied in depth, there is, however, a gap concerning automated model adaptation strategies when multiple strategies are available. Manually…
Paper presents a Transformer model for automatic domain adaptation.
problem Challenges in selecting or designing domain adaptation algorithms.
method Transformer model approximates and selects domain adaptation algorithms.
result Transformers can approximate and automatically select domain adaptation algorithms.
cKAM improves adaptive sampling by incorporating a cyclical stepsize scheme.
problem Adaptive Metropolis algorithms can get stuck in local modes.
method cKAM uses a cyclical stepsize scheme to encourage exploration and escape from local modes.
result cKAM successfully escapes local modes and converges to the true posterior distribution.
Adaptive variational Bayes framework improves inference adaptively.
problem Lack of general and computationally tractable variational Bayes method for adaptive inference.
method Proposes a novel adaptive variational Bayes framework combining variational posteriors over individual models.
result Adaptive variational Bayes achieves optimal contraction rates adaptively under general conditions.
New approach shows AI can adapt like toddlers by correcting old knowledge.
problem Lack of adaptability in AI models compared to humans and animals.
method Casting adaptation as posterior correction and using Bayesian Learning Rule.
result AI can learn to adapt quickly by using posterior correction.
This paper improves neural network generalization by dynamically learning kernel parameters.
problem Improving neural network generalization and adaptability.
method Diagonal adaptive kernel model that learns kernel eigenvalues and output coefficients during training.
result The diagonal adaptive kernel model significantly improves generalization over fixed-kernel methods.
Study on distributed nonparametric function estimation with optimal rate and cost of adaptation.
problem Optimal rate of convergence and cost of adaptation in distributed nonparametric function estimation.
method Distributed minimax estimation and adaptive estimation under communication constraints for Gaussian sequence model and white noise model.
result Established minimax rate of convergence and exact communication cost for adaptation.
This paper explains why Adam generalizes worse than SGD by analyzing its components.
problem Understanding why Adam generalizes worse than Stochastic Gradient Descent (SGD).
method Diffusion theoretical framework to disentangle the effects of Adaptive Learning Rate and Momentum.
result Adaptive Learning Rate helps escape saddle points but not select flat minima, while Momentum provides a drift effect to help pass through saddle points.
New adaptive importance samplers improve stability and accuracy.
problem Improving the stability and accuracy of importance sampling estimators.
method Introducing AdaOAIS, a new adaptive importance sampler using adaptive optimisers to address the instability of OAIS.
result AdaOAIS leads to stable importance sampling estimators in practice.
Adaptive networks improve model robustness through conditional normalization.
problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.
In domain adaptation, classifiers with information from a source domain adapt to generalize to a target domain. However, an adaptive classifier can perform worse than a non-adaptive classifier due to invalid assumptions, increased sensitivity to estimation errors or model misspecification. Our goal is to develop a doma…
FLAP adapts policies quickly to new tasks using shared linear representations.
problem Adapting policies to new tasks efficiently and effectively.
method FLAP uses a shared linear representation and a separate adapter network for quick adaptation.
result FLAP achieves up to 8X faster adaptation and significantly better performance on out-of-distribution tasks.