Counterfactual explanations play an important role in detecting bias and improving the explainability of data-driven classification models. A counterfactual explanation (CE) is a minimal perturbed data point for which the decision of the model changes. Most of the existing methods can only provide one CE, which may not be achievable for the user. In this work we derive an iterative method to calculate robust CEs, i.e. CEs that remain valid even after the features are slightly perturbed. To this end, our method provides a whole region of CEs allowing the user to choose a suitable recourse to obtain a desired outcome. We use algorithmic ideas from robust optimization and prove convergence results for the most common machine learning methods including logistic regression, decision trees, random forests, and neural networks. Our experiments show that our method can efficiently generate globally optimal robust CEs for a variety of common data sets and classification models.

We consider the problem of learning classification trees that are robust to distribution shifts between training and testing/deployment data. This problem arises frequently in high stakes settings such as public health and social work where data is often collected using self-reported surveys which are highly sensitive to e.g., the framing of the questions, the time when and place where the survey is conducted, and the level of comfort the interviewee has in sharing information with the interviewer. We propose a method for learning optimal robust classification trees based on mixed-integer robust optimization technology. In particular, we demonstrate that the problem of learning an optimal robust tree can be cast as a single-stage mixed-integer robust optimization problem with a highly nonlinear and discontinuous objective. We reformulate this problem equivalently as a two-stage linear robust optimization problem for which we devise a tailored solution procedure based on constraint generation. We evaluate the performance of our approach on numerous publicly available datasets, and compare the performance to a regularized, non-robust optimal tree. We show an increase of up to 12.48% in worst-case accuracy and of up to 4.85% in average-case accuracy across several datasets and distribution shifts from using our robust solution in comparison to the non-robust one.

Biases with respect to socially-salient attributes of individuals have been well documented in evaluation processes used in settings such as admissions and hiring. We view such an evaluation process as a transformation of a distribution of the true utility of an individual for a task to an observed distribution and model it as a solution to a loss minimization problem subject to an information constraint. Our model has two parameters that have been identified as factors leading to biases: the resource-information trade-off parameter in the information constraint and the risk-averseness parameter in the loss function. We characterize the distributions that arise from our model and study the effect of the parameters on the observed distribution. The outputs of our model enrich the class of distributions that can be used to capture variation across groups in the observed evaluations. We empirically validate our model by fitting real-world datasets and use it to study the effect of interventions in a downstream selection task. These results contribute to an understanding of the emergence of bias in evaluation processes and provide tools to guide the deployment of interventions to mitigate biases.

In many practical learning scenarios, there is a discrepancy between the training and testing distribution. For instance, when training large language models, we may have access to a training set that contains many low-quality data points from different sources and want to train a model on this dataset to perform well on a testing set that contains a few high-quality points [7, 3, 18]. An appealing way to solve this problem is data reweighting [21, 23, 26], where one attributes one weight to each data point in the training set. The weight of a training sample should reflect how much this sample resembles the testing set and helps the model perform well on it. Figure 1 illustrates the general principle. Learning the optimal weights can be cast as a bilevel optimization problem [9], where the optimal weights are such that training the model with these weights leads to the smallest test loss possible. The weights are usually constrained to sum to one, leading to an optimization problem on the simplex, which is usually solved with mirror descent [19].

The optimal robot assembly planning problem is challenging due to the necessity of finding the optimal solution amongst an exponentially vast number of possible plans, all while satisfying a selection of constraints. Traditionally, robotic assembly planning problems have been solved using heuristics, but these methods are specific to a given objective structure or set of problem parameters. In this paper, we propose a novel approach to robotic assembly planning that poses assembly sequencing as a sequential decision making problem, enabling us to harness methods that far outperform the state-of-the-art. We formulate the problem as a Markov Decision Process (MDP) and utilize Dynamic Programming (DP) to find optimal assembly policies for moderately sized strictures. We further expand our framework to exploit the deterministic nature of assembly planning and introduce a class of optimal Graph Exploration Assembly Planners (GEAPs). For larger structures, we show how Reinforcement Learning (RL) enables us to learn policies that generate high reward assembly sequences. We evaluate our approach on a variety of robotic assembly problems, such as the assembly of the Hubble Space Telescope, the International Space Station, and the James Webb Space Telescope. We further showcase how our DP, GEAP, and RL implementations are capable of finding optimal solutions under a variety of different objective functions and how our formulation allows us to translate precedence constraints to branch pruning and thus further improve performance. We have published our code at https://github.com/labicon/ORASP-Code.

Transformers are remarkably good at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they perform ICL remains a mystery. Recent work suggests that Transformers may learn in-context by internally running Gradient Descent, a first-order optimization method. In this paper, we instead demonstrate that Transformers learn to implement higher-order optimization methods to perform ICL. Focusing on in-context linear regression, we show that Transformers learn to implement an algorithm very similar to Iterative Newton's Method, a higher-order optimization method, rather than Gradient Descent. Empirically, we show that predictions from successive Transformer layers closely match different iterations of Newton's Method linearly, with each middle layer roughly computing 3 iterations. In contrast, exponentially more Gradient Descent steps are needed to match an additional Transformers layer; this suggests that Transformers have an comparable rate of convergence with high-order methods such as Iterative Newton, which are exponentially faster than Gradient Descent. We also show that Transformers can learn in-context on ill-conditioned data, a setting where Gradient Descent struggles but Iterative Newton succeeds. Finally, we show theoretical results which support our empirical findings and have a close correspondence with them: we prove that Transformers can implement $k$ iterations of Newton's method with $\mathcal{O}(k)$ layers.

In predictive modeling with simulation or machine learning, it is critical to accurately assess the quality of estimated values through output analysis. In recent decades output analysis has become enriched with methods that quantify the impact of input data uncertainty in the model outputs to increase robustness. However, most developments are applicable assuming that the input data adheres to a parametric family of distributions. We propose a unified output analysis framework for simulation and machine learning outputs through the lens of Monte Carlo sampling. This framework provides nonparametric quantification of the variance and bias induced in the outputs with higher-order accuracy. Our new bias-corrected estimation from the model outputs leverages the extension of fast iterative bootstrap sampling and higher-order influence functions. For the scalability of the proposed estimation methods, we devise budget-optimal rules and leverage control variates for variance reduction. Our theoretical and numerical results demonstrate a clear advantage in building more robust confidence intervals from the model outputs with higher coverage probability.

Many machine learning problems involve the challenge of approximating an intractable target distribution, which might only be known up to a normalization constant. Bayesian inference is a typical example, where the intractable and unnormalized target distribution is a result of the product of the prior and likelihood functions (see [11, 18, 4]). Variational Inference (VI), a widely employed across various application domains, seeks to approximate this intractable target distribution by utilizing a variational distribution (see [3, 7, 20] and references therein). VI is typically formulated as an optimization problem, with the objective of maximizing the evidence lower bound objective (ELBO), which is equivalent to minimizing the Kullback-Leiber (KL) divergence between the variational distribution and the target distribution. The conventional method for maximizing the ELBO involves the use of gradient descent, such as black-box VI (BBVI, [16]). The gradient of the ELBO can be expressed as an expectation over the variational distribution, which is typically estimated by Monte Carlo samples from this distribution.

Federated learning is a popular distributed and privacy-preserving machine learning paradigm. Meanwhile, minimax optimization, as an effective hierarchical optimization, is widely applied in machine learning. Recently, some federated optimization methods have been proposed to solve the distributed minimax problems. However, these federated minimax methods still suffer from high gradient and communication complexities. Meanwhile, few algorithm focuses on using adaptive learning rate to accelerate algorithms. To fill this gap, in the paper, we study a class of nonconvex minimax optimization, and propose an efficient adaptive federated minimax optimization algorithm (i.e., AdaFGDA) to solve these distributed minimax problems. Specifically, our AdaFGDA builds on the momentum-based variance reduced and local-SGD techniques, and it can flexibly incorporate various adaptive learning rates by using the unified adaptive matrix. Theoretically, we provide a solid convergence analysis framework for our AdaFGDA algorithm under non-i.i.d. setting. Moreover, we prove our algorithms obtain lower gradient (i.e., stochastic first-order oracle, SFO) complexity of $\tilde{O}(\epsilon^{-3})$ with lower communication complexity of $\tilde{O}(\epsilon^{-2})$ in finding $\epsilon$-stationary point of the nonconvex minimax problems. Experimentally, we conduct some experiments on the deep AUC maximization and robust neural network training tasks to verify efficiency of our algorithms.

Quantum computing (QC) is a field that has witnessed a rapid increase in interest and development over the past few decades since it was theoretically shown that quantum computers can provide an exponential speedup for certain tasks (Deutsch, Jozsa 1992; Grover 1996; Shor 1994). Translating this potential into a practically relevant quantum advantage, however, has proven to be a very challenging endeavor. Nevertheless, the emerging field is considered to have a highly disruptive potential for many domains, for example in machine learning (Schuld, Sinayskiy, Petruccione 2015), chemical simulations (Cao et al. 2019) and optimization (Li et al. 2020), the domain of this work. Due to the fact that optimization problems are of utmost importance also for industrial applications, we investigated a potential advantage of quantum and quantum-inspired technology for the so-called transport robot scheduling problem (TRSP), a real-world use-case in optimization that is derived from an industrial application of an automatized robot in a high-throughput laboratory. The optimization task is to plan a time-efficient schedule for the robot's movements as it transports chemical samples between a rack and multiple machines to conduct experiments.