A new framework improves reinforcement learning algorithms with policy guarantees.
problem Designing efficient and stable reinforcement learning algorithms.
method A general framework (FMA-PG) based on functional mirror ascent that constructs surrogate functions enabling policy improvement guarantees.
result The proposed framework enables policy improvement guarantees that hold regardless of policy parameterization, and recovers important heuristics.
Paper introduces new loss functions for multi-class abstention learning.
problem Learning with multi-class classification and the ability to abstain.
method Developed new families of surrogate losses for abstention.
result Proved strong consistency guarantees for new surrogate losses.
Empirical risk minimization frequently employs convex surrogates to underlying discrete loss functions in order to achieve computational tractability during optimization. However, classical convex surrogates can only tightly bound modular loss functions, sub-modular functions or supermodular functions separately while …
This paper develops efficient surrogate models for optimization of complex dynamical systems.
problem Computational expense in solving complex dynamical systems through numerical simulation.
method Combination of proper orthogonal decomposition and radial basis functions for constructing low-dimensional surrogate models.
result Surrogate models reduce computational time for optimization problems while maintaining accuracy.
Generalizes NTK for surrogate gradient learning in neural networks.
problem Lack of theoretical foundation for surrogate gradient learning.
method Generalizes neural tangent kernel (NTK) for surrogate gradient learning (SGL).
result Surrogate gradient NTK provides a good characterization of SGL.
A new method for incorporating preferences in multi-objective Bayesian optimization.
problem Incorporating preferences in computationally expensive multi-objective optimization problems.
method Building independent surrogate models on each objective function and using Generalised value distribution to approximate the scalarizing function.
result The proposed multi-surrogate approach outperforms the mono-surrogate approach on benchmark and real-world problems.
Learning with non-modular losses is an important problem when sets of predictions are made simultaneously. The main tools for constructing convex surrogate loss functions for set prediction are margin rescaling and slack rescaling. In this work, we show that these strategies lead to tight convex surrogates iff the unde…
The study develops a theory for structured prediction using smooth convex surrogates.
problem Developing a theoretical framework for structured prediction.
method Characterizing smooth convex surrogates compatible with task losses and deriving statistical guarantees.
result Derives tight bounds for the calibration function and novel results for existing surrogate frameworks.
We develop a framework for consistent polyhedral surrogates in classification and prediction.
problem Designing consistent polyhedral surrogates for classification and prediction problems.
method Formalizing and studying embeddings of predictions as points in R^d, assigning original loss values, and convexifying to create surrogates.
result Established a strong connection between embeddings and polyhedral surrogates, providing constructions and proofs of consistency or inconsistency.
POAP and pySOT improve surrogate optimization of expensive functions.
problem Optimizing expensive functions with concurrent evaluations.
method Event-driven asynchronous framework for optimization strategies.
result Asynchronous computation offers significant speed-up advantages.
Study of loss functions for learning to defer, proving consistency.
problem Learning to defer in machine learning.
method Introduced a family of surrogate losses parameterized by Ψ and proved their consistency. result Proved realizable H-consistency and Bayes-consistency of specific surrogate losses. Develops a numerical algorithm for stochastic impulse control using regression surrogates.
problem Optimal impulse control in stochastic processes.
method Generates statistical surrogates for continuation and intervention functions, recursively trained over simulated state trajectories.
result Demonstrates flexibility and extensibility of the numerical scheme through case studies.
Paper proposes a method to minimize non-differentiable loss functions.
problem Minimizing non-differentiable and non-decomposable loss functions.
method Learn smooth relaxations of true losses through surrogate neural networks, then optimize jointly with the prediction model.
result Empirical results show the efficiency of learning surrogate losses.
New bounds show polyhedral surrogates are optimal for generalization.
problem Proving generalization rates for polyhedral loss functions.
method Developed two general results for polyhedral surrogates.
result Polyhedral surrogates provide linear surrogate regret bounds, translating directly to target rates.
We study the rates of convergence from empirical surrogate risk minimizers to the Bayes optimal classifier. Specifically, we introduce the notion of \emph{consistency intensity} to characterize a surrogate loss function and exploit this notion to obtain the rate of convergence from an empirical surrogate risk minimizer…
Meta-model framework improves efficiency in parameter estimation of dynamical systems.
problem Efficiently estimating parameters of complex dynamical systems with computationally expensive objective functions.
method Dynamic adaptation of surrogate model and substitution strategy using a meta-model framework.
result Significant improvement in optimization efficiency, reducing evaluations by up to 77%.
This paper investigates the control of an ML component within the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) devoted to black-box optimization. The known CMA-ES weakness is its sample complexity, the number of evaluations of the objective function needed to approximate the global optimum. This weakness is…
In this paper we refine the process of computing calibration functions for a number of multiclass classification surrogate losses. Calibration functions are a powerful tool for easily converting bounds for the surrogate risk (which can be computed through well-known methods) into bounds for the true risk, the probabili…
Study proposes a differentiable surrogate loss function for optimizing Fβ score in binary classification with imbalanced data.
problem Non-differentiability of Fβ score makes it unsuitable for optimization by gradient-based learning. method Investigated relationship between Fβ score and loss functions, proposed a differentiable surrogate loss function. result Gradient paths of the proposed surrogate Fβ loss function approximate the gradient paths of the Fβ score. We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, o…
Study on learning to defer with multiple experts using new surrogate losses.
problem Learning to defer with multiple experts in a machine learning context.
method Introducing a new family of surrogate losses for the multiple-expert setting, proving H-consistency bounds, and designing learning algorithms. result Explicit guarantees for new learning to defer algorithms based on minimization of these surrogate losses.
Optimizes expensive functions using adaptive RBF surrogate model.
problem Global optimization of expensive, possibly non-differentiable functions.
method Adaptive Radial Basis Function (RBF) surrogate model with uncertainty quantification.
result The proposed method identifies optimal points efficiently, especially for non-smooth surfaces.
AEGiS optimizes expensive function evaluations asynchronously.
problem Optimizing expensive black-box functions efficiently.
method Asynchronous ε-Greedy Bayesian Optimisation combining greedy search and Thompson sampling.
result AEGiS outperforms existing asynchronous BO methods.
The paper surveys methods to approximate non-negative matrices using lower-dimensional factors.
problem Approximating high-dimensional non-negative matrices with lower-dimensional factors.
method Alternating minimization with surrogate functionals for Tikhonov functionals.
result Developed a general framework for adding penalty terms to surrogate functionals.
SBBO optimizes complex spaces using sampling-based models.
problem Optimizing complex spaces with discrete variables.
method Simulation Based Bayesian Optimization (SBBO) using sampling-based surrogate models.
result Empirical effectiveness of SBBO in combinatorial optimization.
Improves Bayesian optimization by focusing on well-behaved structure in objectives.
problem Bayesian optimization struggles with real-world objectives that are often poorly behaved.
method Proposes surrogate models that focus on well-behaved structure, absorbing challenging structures as irreducible uncertainty.
result Surrogate models with appropriate noise distributions improve reliability and performance in challenging objective functions.
Gradient-informed BNNs improve Bayesian optimization performance.
problem Improving Bayesian optimization with gradient information.
method Gradient-informed loss function for Bayesian neural networks.
result Gradient information enhances BNN predictions and BO convergence.
Improved machine learning model performance through data augmentation, custom loss functions, and transfer learning.
problem Poor performance of a traditional engineering model due to limited training data.
method Data augmentation, custom loss functions, transfer learning.
result Improvement of at least 38% in performance across five models.
This paper proposes a mechanism to produce equivalent Lipschitz surrogates for zero-norm and rank optimization problems by means of the global exact penalty for their equivalent mathematical programs with an equilibrium constraint (MPECs). Specifically, we reformulate these combinatorial problems as equivalent MPECs by…
New framework quantifies learning guarantees for inconsistent convex surrogates.
problem Analyzing consistency properties of machine learning methods with inconsistent convex surrogates.
method Extending the framework of Osokin et al. (2017) to inconsistent surrogates, introducing a new lower bound on the calibration function.
result Shows how learning with inconsistent surrogates can have guarantees on sample complexity and optimization difficulty.
This paper tackles deferral learning with multiple experts, providing strong theoretical guarantees.
problem Optimizing input assignment to experts balancing accuracy and computational cost.
method Introducing new surrogate loss functions and efficient algorithms with strong theoretical learning guarantees.
result Realizable H-consistency, H-consistency bounds, and Bayes-consistency for deferral learning. GUESS improves surrogate model accuracy with adaptive sampling.
problem Creating accurate surrogate models with limited data.
method Gradient and Uncertainty Enhanced Sequential Sampling (GUESS) using predictive uncertainty and Taylor expansion.
result GUESS achieved highest sample efficiency compared to other strategies.
We present surrogate regret bounds for arbitrary surrogate losses in the context of binary classification with label-dependent costs. Such bounds relate a classifier's risk, assessed with respect to a surrogate loss, to its cost-sensitive classification risk. Two approaches to surrogate regret bounds are developed. The…
Algorithm leverages low-rank relations between surrogate tasks for structured prediction.
problem Structured prediction with large or infinite-dimensional surrogate spaces.
method Trace norm regularization to leverage relationships between surrogate outputs without explicit coding/decoding functions.
result Our algorithm can improve generalization performance over previous methods.
New method extends surrogate modeling to high dimensions using dimensionality reduction.
problem Curse of dimensionality limits surrogate models to low dimensions.
method Combines Kriging, polynomial chaos expansions, and kernel PCA for high-dimensional problems.
result High-dimensional problems can be solved using the proposed method.
BITS for GAPS uses Bayesian methods to improve surrogate model accuracy in complex systems.
problem Improving surrogate model accuracy in complex physical systems with uncertainty.
method Bayesian Information-Theoretic Sampling for hierarchical Gaussian Process Surrogates.
result Increased expected information gain and predictive accuracy by targeting high-uncertainty regions.
GLIS uses IDW and RBF for efficient global optimization.
problem Expensive objective function in optimization problems.
method Combines inverse distance weighting and radial basis functions for acquisition function.
result Competitive and computationally lighter than Bayesian optimization.
Proposes a framework for creating custom surrogate explanations.
problem Misunderstanding of LIME as the solution for surrogate explanations.
method Decomposes surrogate explainers into algorithmically independent modules.
result Empowers researchers to create custom local surrogate explanations.
Active learning is a type of sequential design for supervised machine learning, in which the learning algorithm sequentially requests the labels of selected instances from a large pool of unlabeled data points. The objective is to produce a classifier of relatively low risk, as measured under the 0-1 loss, ideally usin…
Develops Co_SVR for multi-fidelity modeling combining HF and LF models.
problem Combining high-fidelity and low-fidelity models for efficient design.
method Support vector regression with kernel function and heuristic algorithm.
result Co_SVR outperforms other multi-fidelity surrogate models in prediction accuracy.
AUC (area under ROC curve) is an important evaluation criterion, which has been popularly used in many learning tasks such as class-imbalance learning, cost-sensitive learning, learning to rank, etc. Many learning approaches try to optimize AUC, while owing to the non-convexity and discontinuousness of AUC, almost all …
Surrogate-based analysis of interactions via local effect smooths
problem Detecting and characterizing feature interactions in machine learning models
method Surrogate-based analysis using generalized additive models
result Empirical validation of effectiveness for pairwise interactions
Safe reinforcement learning with nonconvex constraints using convex approximations.
problem Safe reinforcement learning with nonlinear function approximation.
method Constructing surrogate convex constrained optimization problems by replacing nonconvex functions with convex quadratic functions.
result Solutions to surrogate problems converge to a stationary point of the original nonconvex problem.
Unified approach for federated learning using MM optimization.
problem Scaling stochastic optimization to federated learning.
method Unified Majorize-Minimize (MM) framework for stochastic optimization, extended to federated learning.
result Unified algorithm \QSMM\ for federated learning that aggregates surrogate majorizing functions.
New method simplifies checking consistency of differentiable loss functions.
problem Verifying consistency of differentiable loss functions is difficult.
method Developed a new approach called strong indirect elicitation (strong IE) to simplify checking consistency.
result Strong IE is equivalent to calibration for strongly convex, differentiable surrogates.
Optimizes hard-to-optimize metrics using adaptive surrogates.
problem Training models with black-box and hard-to-optimize metrics.
method Expresses metric as a function of surrogates, solves optimization problem over relaxed surrogate space.
result Approach performs on par with known methods and adds value when metric form is unknown.
Linear-Core Surrogates combine fast optimization and statistical efficiency in classification and structured prediction.
problem The trade-off between smoothness and margin-based losses in classification and structured prediction.
method Linear-Core (LC) Surrogates, a family of convex loss functions that stitch a linear core to a smooth tail.
result LC Surrogates achieve fast linear consistency rates while maintaining differentiability and strict H-consistency bounds. Automatically searching for optimal hyperparameter configurations is of crucial importance for applying deep learning algorithms in practice. Recently, Bayesian optimization has been proposed for optimizing hyperparameters of various machine learning algorithms. Those methods adopt probabilistic surrogate models like G…