Investigates numerical issues in GP interpolation parameter estimation.
problem Numerical issues in maximum likelihood parameter estimation for Gaussian process interpolation.
method Investigates and proposes strategies to improve open-source software implementations.
result Improves reliability and reproducibility of studies relying on GP implementations.
KL-constrained API shows optimization issues and improved with regularization.
problem Optimization issues in KL-constrained API algorithms.
method Comparison of KL divergence as a constraint vs. regularizer, empirical evaluation.
result KL-constrained API is not guaranteed to converge and incurs linear regret.
This paper explores optimization methods for deep learning.
problem How to effectively train neural networks.
method Discusses gradient explosion/vanishing, initialization, normalization, SGD, adaptive gradient methods, distributed methods, and global issues.
result Provides theoretical insights and practical solutions for neural network training.
While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature. To address this issue, several highly flexible and scalable variational inference procedures based on the idea of particle optimization have be…
FDS tackles long horizon hyperparameter optimization issues.
problem Memory scaling and gradient degradation in long horizon tasks.
method Forward-mode differentiation with sharing (FDS).
result Significantly outperforms greedy gradient-based alternatives.
This paper examines linear embeddings for high-dimensional Bayesian optimization, identifying and addressing issues to improve performance.
problem Scaling Bayesian optimization to high-dimensional spaces while maintaining sample efficiency.
method Study and empirical evaluation of linear embeddings for BO, addressing design choices and their impact on performance.
result Properly addressing issues in linear embeddings significantly improves their efficacy in BO.
We consider the issue of solution uniqueness for portfolio optimization problem and its inverse for asset returns with a finite number of possible scenarios. The risk is assessed by deviation measures introduced by [Rockafellar et al., Mathematical Programming, Ser. B, 108 (2006), pp. 515-540] instead of variance as in…
Proposes m-POT to improve m-OT's misspecified mappings issue.
problem Misspecified mappings in mini-batch optimal transport.
method Partial optimal transport (POT) between mini-batch empirical measures.
result m-POT alleviates incorrect mappings compared to current methods.
We consider the problem of computing optimal policies in average-reward Markov decision processes. This classical problem can be formulated as a linear program directly amenable to saddle-point optimization methods, albeit with a number of variables that is linear in the number of states. To address this issue, recent …
Optimal microlending group size is 5 people.
problem Determining the best group size for microlending to minimize default risk.
method Mathematical modeling with interacting forces and precise hypotheses.
result The optimal microlending group size is 5 people.
Proposes ESCFR to estimate treatment effects from biased data.
problem Treatment selection bias in observational data.
method Stochastic optimal transport with relaxed mass-preserving and proximal factual outcome regularizers.
result Significantly better performance in estimating treatment effects.
This paper improves Bayesian optimization methods with tighter regret bounds and practical solutions.
problem Improving Bayesian optimization methods with tighter regret bounds and practical solutions.
method The paper analyzes and compares different acquisition functions (GP-UCB, TS, PIMS) to achieve tighter Bayesian cumulative regret bounds and address practical issues.
result PIMS achieves the tighter BCR bound and avoids hyperparameter tuning, unlike GP-UCB and TS.
CRA improves UL-based CO solvers by dynamically smoothing and enforcing discreteness.
problem Local optima and artificial rounding issues in UL-based CO solvers.
method Continuous Relaxation Annealing (CRA) strategy that dynamically shifts from continuous to discrete solutions.
result Significantly enhances UL-based CO solver performance and eliminates artificial rounding.
Differentiable methods fail due to spectral issues in Jacobians.
problem Chaos-based failures in differentiable programming.
method Trace failures to the spectrum of Jacobians.
result Criteria for avoiding spectral failure in optimization.
We study issues of robustness in the context of Quantitative Risk Management and Optimization. We develop a general methodology for determining whether a given risk measurement related optimization problem is robust, which we call "robustness against optimization". The new notion is studied for various classes of risk …
We address the problem of synthetic gene design using Bayesian optimization. The main issue when designing a gene is that the design space is defined in terms of long strings of characters of different lengths, which renders the optimization intractable. We propose a three-step approach to deal with this issue. First, …
Generative Adversarial Networks (GANs) have become a popular method to learn a probability model from data. In this paper, we aim to provide an understanding of some of the basic issues surrounding GANs including their formulation, generalization and stability on a simple benchmark where the data has a high-dimensional…
Scalable3-BO tackles scalability issues in Bayesian optimization for big data and high dimensions.
problem Bayesian optimization scalability issues in big data and high dimensions.
method Sparse Gaussian process, random embedding, asynchronous parallelization.
result Scalable3-BO framework optimizes high-dimensional problems with 1 million data points and 10,000 dimensions.
Paper identifies objective mismatch in MBRL, affecting control task performance.
problem Objective mismatch in MBRL framework affects control task performance.
method Proposes re-weighting dynamics model training to mitigate mismatch.
result Likelihood of one-step ahead predictions is not always correlated with control performance.
Proposes MamBO for efficient high-dimensional large-scale optimization.
problem High-dimensional and large-scale optimization problems in machine learning and simulation.
method Combines subsampling and subspace embeddings with model aggregation to address uncertainty in surrogate models.
result Improves robustness of Bayesian optimization algorithm and achieves superior performance.
This paper reviews recent advancements in amortized Variational Inference.
problem Scalability and efficiency issues in traditional Variational Inference.
method Systematic review of various Variational Inference techniques, focusing on amortized approaches.
result Amortized Variational Inference improves scalability and efficiency for generative modeling tasks.
MiM-StocR combines momentum indicators and adaptive ranking loss for better stock recommendation.
problem Lack of simultaneous short-term trend and ranking prediction in stock recommendation models.
method Integrates momentum indicators and proposes Adaptive-k ApproxNDCG for ranking optimization.
result MiM-StocR outperforms state-of-the-art MTL baselines in stock recommendation.
These notes constitute a sort of Crash Course in Optimal Transport Theory. The different features of the problem of Monge-Kantorovitch are treated, starting from convex duality issues. The main properties of space of probability measures endowed with the distances Wp induced by optimal transport are detailed. The ke…
This work examines consistency issues in Gaussian Mixture Model reduction algorithms.
problem Consistency issues in Gaussian Mixture Model reduction algorithms.
method Discussion of the importance of dissimilarity measure choice and consistency of GMR algorithms.
result Most existing GMR algorithms are not consistent with a unique measure, leading to suboptimal reduced GMs.
Proposes a new framework for optimizing utility with state-dependent benchmarks.
problem Various interpretations of benchmarks in utility functions.
method General framework of state-dependent utility optimization with stochastic benchmarks.
result Provides optimal solutions and addresses issues of well-definedness and feasibility.
The adaptive moment estimation algorithm Adam (Kingma and Ba) is a popular optimizer in the training of deep neural networks. However, Reddi et al. have recently shown that the convergence proof of Adam is problematic and proposed a variant of Adam called AMSGrad as a fix. In this paper, we show that the convergence pr…
A DRL approach optimizes resource allocation in BFL to reduce latency and energy consumption.
problem Energy and CPU constraints of mobile devices and increased training latency due to blockchain mining.
method Deep Reinforcement Learning (DRL) to derive optimal decisions for MLMO.
result Optimal resource allocation and block generation rate to minimize system latency, energy consumption, and incentive cost.
This paper tackles efficient optimization for nonlinear embeddings in similarity learning.
problem Learning similarity with nonlinear embeddings is challenging due to the large number of pairs.
method Detailed derivations and efficient optimization methods for nonlinear embeddings are developed.
result Efficient optimization methods for nonlinear embeddings are shown to be highly effective.
New approach to optimal income tax theory tackles inequity issues.
problem Optimal tax schedules often lead to minimal tax rates for higher earners, contradicting ethical practices.
method Developed a theorem for piecewise-linear environment and introduced a new utility function parameter.
result New approach leads to more equitable tax schedules, interpreting optimality criteria easily.
A new portfolio model improves on Kelly's by accounting for estimation error.
problem Estimation error in Kelly portfolio optimization.
method Wasserstein distributionally robust optimization (DRO) to define a robust log-optimal portfolio.
result The Wasserstein-Kelly portfolio outperforms the Kelly portfolio in out-of-sample testing.
Develops a framework for cost-efficient Bayesian optimization with constraints.
problem Optimizing designs with minimal cost in constrained search spaces.
method Constrained multi-fidelity Bayesian optimization (CMFBO) with automatic stopping criterion.
result Minimizes overall sampling costs while ensuring feasibility.
Lo-Hp decouples weight generation into local and global policies to improve flexibility and efficiency.
problem Over-coupling and long-horizon issues in current optimization methods.
method Hybrid-Policy Sub-Trajectory Balance objective.
result Learning local optimization policies addresses long-horizon issues and enhances global weight generation.
The paper tackles scalarization issues in A2C RL algorithms, proposing methods to avoid gradient overlap and noise.
problem Scalarization issues in A2C RL algorithms leading to gradient overlap and uncontrolled noise.
method Proposes techniques to avoid gradient overlap and noise in A2C RL algorithms.
result Pilot experiments show the proposed method speeds up training in A2C RL algorithms.
Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradient updates scaled by square roots of exponential moving averages of squared past gradients. In many applications, e.g. learning with large …
Investigates how rebalancing frequency and transaction costs affect log-optimal portfolios.
problem Impact of rebalancing frequency and transaction costs on log-optimal portfolios.
method Proved equivalence to concave program, derived optimality conditions, tested using intraday and daily data.
result Transaction costs can cause bankruptcy for frequency-dependent log-optimal portfolios, approximating to quadratic concave program.
NOT learns optimal transport plans, kernel costs improve performance.
problem NOT algorithm learns non-optimal plans with weak quadratic costs.
method Introduced kernel weak quadratic costs to improve NOT's performance.
result Kernel costs provide improved theoretical and practical guarantees.
A key issue in the estimation of energy hedges is the hedgers' attitude towards risk which is encapsulated in the form of the hedgers' utility function. However, the literature typically uses only one form of utility function such as the quadratic when estimating hedges. This paper addresses this issue by estimating an…
New method escapes local optima in neural architecture optimization.
problem Escaping local optima in neural architecture optimization.
method Signed neural splitting in steepest descent framework.
result Escapes local optima, leading to better performance.
This paper tackles ranking-based performance normalization for optimization algorithms.
problem Ranking optimization algorithms across diverse numerical scales disrupts performance comparisons.
method Introduces absolute ranking and a sampling-based computational method to address numerical scale variation.
result Provides a more robust framework for assessing performance across multiple algorithms and problems.
Estimates rewards from a demonstrator's learning process.
problem Estimating rewards from a demonstrator's behavior.
method Leveraging the demonstrator's exploration phase for reward estimation.
result Consistent reward estimation possible without identifiability issues.
Proposes a method to identify elements in a skewness matrix for multivariate skew-elliptical distributions.
problem Label switching issue in Bayesian estimation of skewness matrix.
method Imposes a positive lower-triangular constraint and uses Bayesian sparse estimation with horseshoe prior.
result Successfully estimates the true structure of skewness dependency.
The study examines portfolio optimization with quadratic transaction costs, complicating the optimization process.
problem Portfolio optimization with quadratic transaction costs is more challenging than with linear costs.
method Introduced numerical algorithms to solve the optimization problem with quadratic transaction costs.
result Quadratic transaction costs significantly impact the expected returns of optimized portfolios.
Paper proposes a new method for regression using optimal transport cost optimization.
problem Regression problem, especially with complex noise forms.
method Directly optimizes the optimal transport cost between true and estimated distributions.
result Achieves state-of-the-art results on various datasets.
Proposes a method to enforce nestedness in subspace learning methods.
problem Consistency between data representations when choosing different subspaces dimensions.
method Lifts Grassmannian optimization criteria to flag manifolds via nested projectors.
result Successfully addresses the nestedness issue in several machine learning methods.
When function approximation is deployed in reinforcement learning (RL), the same problem may be formulated in different ways, often by treating a pre-processing step as a part of the environment or as part of the agent. As a consequence, fundamental concepts in RL, such as (optimal) value functions, are not uniquely de…
Generative adversarial nets (GANs) have generated a lot of excitement. Despite their popularity, they exhibit a number of well-documented issues in practice, which apparently contradict theoretical guarantees. A number of enlightening papers have pointed out that these issues arise from unjustified assumptions that are…
New methods improve multi-agent reinforcement learning by addressing rotational dynamics.
problem Reproducibility crisis in multi-agent reinforcement learning.
method Reframing MARL approaches using Variational Inequalities (VIs) and proposing gradient-based VI methods.
result Significant performance improvements across benchmarks, including better convergence to equilibrium strategies in zero-sum games.
Paper improves RL from imperfect demonstrations with soft expert guidance.
problem Improper and insufficient expert demonstrations in RLfD.
method Formalizes imperfect expert setting, tackles optimality and convergence issues with soft constraints, and uses local linear search on dual form.
result Method achieves consistent improvement over other RLfD methods.