Neural networks are successful in various applications but are also susceptible to adversarial attacks. To show the safety of network classifiers, many verifiers have been introduced to reason about the local robustness of a given input to a given perturbation. While successful, local robustness cannot generalize to unseen inputs. Several works analyze global robustness properties, however, neither can provide a precise guarantee about the cases where a network classifier does not change its classification. In this work, we propose a new global robustness property for classifiers aiming at finding the minimal globally robust bound, which naturally extends the popular local robustness property for classifiers. We introduce VHAGaR, an anytime verifier for computing this bound. VHAGaR relies on three main ideas: encoding the problem as a mixed-integer programming and pruning the search space by identifying dependencies stemming from the perturbation or the network's computation and generalizing adversarial attacks to unknown inputs. We evaluate VHAGaR on several datasets and classifiers and show that, given a three hour timeout, the average gap between the lower and upper bound on the minimal globally robust bound computed by VHAGaR is 1.9, while the gap of an existing global robustness verifier is 154.7. Moreover, VHAGaR is 130.6x faster than this verifier. Our results further indicate that leveraging dependencies and adversarial attacks makes VHAGaR 78.6x faster.

Conformal prediction builds marginally valid prediction intervals which cover the unknown outcome of a randomly drawn new test point with a prescribed probability. In practice, a common scenario is that, after seeing the test unit(s), practitioners decide which test unit(s) to focus on in a data-driven manner, and wish to quantify the uncertainty for the focal unit(s). In such cases, marginally valid prediction intervals for these focal units can be misleading due to selection bias. This paper presents a general framework for constructing a prediction set with finite-sample exact coverage conditional on the unit being selected. Its general form works for arbitrary selection rules, and generalizes Mondrian Conformal Prediction to multiple test units and non-equivariant classifiers. We then work out computationally efficient implementation of our framework for a number of realistic selection rules, including top-K selection, optimization-based selection, selection based on conformal p-values, and selection based on properties of preliminary conformal prediction sets. The performance of our methods is demonstrated via applications in drug discovery and health risk prediction.

Existing causal discovery methods based on combinatorial optimization or search are slow, prohibiting their application on large-scale datasets. In response, more recent methods attempt to address this limitation by formulating causal discovery as structure learning with continuous optimization but such approaches thus far provide no statistical guarantees. In this paper, we show that by efficiently parallelizing existing causal discovery methods, we can in fact scale them to thousands of dimensions, making them practical for substantially larger-scale problems. In particular, we parallelize the LiNGAM method, which is quadratic in the number of variables, obtaining up to a 32-fold speed-up on benchmark datasets when compared with existing sequential implementations. Specifically, we focus on the causal ordering subprocedure in DirectLiNGAM and implement GPU kernels to accelerate it. This allows us to apply DirectLiNGAM to causal inference on large-scale gene expression data with genetic interventions yielding competitive results compared with specialized continuous optimization methods, and Var-LiNGAM for causal discovery on U.S. stock data.

We consider \emph{random linear programs} (rlps) as a subclass of \emph{random optimization problems} (rops) and study their typical behavior. Our particular focus is on appropriate linear objectives which connect the rlps to the mean widths of random polyhedrons/polytopes. Utilizing the powerful machinery of \emph{random duality theory} (RDT) \cite{StojnicRegRndDlt10}, we obtain, in a large dimensional context, the exact characterizations of the program's objectives. In particular, for any $\alpha=\lim_{n\rightarrow\infty}\frac{m}{n}\in(0,\infty)$, any unit vector $\mathbf{c}\in{\mathbb R}^n$, any fixed $\mathbf{a}\in{\mathbb R}^n$, and $A\in {\mathbb R}^{m\times n}$ with iid standard normal entries, we have \begin{eqnarray*} \lim_{n\rightarrow\infty}{\mathbb P}_{A} \left ( (1-\epsilon) \xi_{opt}(\alpha;\mathbf{a}) \leq \min_{A\mathbf{x}\leq \mathbf{a}}\mathbf{c}^T\mathbf{x} \leq (1+\epsilon) \xi_{opt}(\alpha;\mathbf{a}) \right ) \longrightarrow 1, \end{eqnarray*} where \begin{equation*} \xi_{opt}(\alpha;\mathbf{a}) \triangleq \min_{x>0} \sqrt{x^2- x^2 \lim_{n\rightarrow\infty} \frac{\sum_{i=1}^{m} \left ( \frac{1}{2} \left (\left ( \frac{\mathbf{a}_i}{x}\right )^2 + 1\right ) \mbox{erfc}\left( \frac{\mathbf{a}_i}{x\sqrt{2}}\right ) - \frac{\mathbf{a}_i}{x} \frac{e^{-\frac{\mathbf{a}_i^2}{2x^2}}}{\sqrt{2\pi}} \right ) }{n} }. \end{equation*} For example, for $\mathbf{a}=\mathbf{1}$, one uncovers \begin{equation*} \xi_{opt}(\alpha) = \min_{x>0} \sqrt{x^2- x^2 \alpha \left ( \frac{1}{2} \left ( \frac{1}{x^2} + 1\right ) \mbox{erfc} \left ( \frac{1}{x\sqrt{2}}\right ) - \frac{1}{x} \frac{e^{-\frac{1}{2x^2}}}{\sqrt{2\pi}} \right ) }. \end{equation*} Moreover, $2 \xi_{opt}(\alpha)$ is precisely the concentrating point of the mean width of the polyhedron $\{\mathbf{x}|A\mathbf{x} \leq \mathbf{1}\}$.

We investigate the empirical counterpart of group distributionally robust optimization (GDRO), which aims to minimize the maximal empirical risk across $m$ distinct groups. We formulate empirical GDRO as a $\textit{two-level}$ finite-sum convex-concave minimax optimization problem and develop a stochastic variance reduced mirror prox algorithm. Unlike existing methods, we construct the stochastic gradient by per-group sampling technique and perform variance reduction for all groups, which fully exploits the $\textit{two-level}$ finite-sum structure of empirical GDRO. Furthermore, we compute the snapshot and mirror snapshot point by a one-index-shifted weighted average, which distinguishes us from the naive ergodic average. Our algorithm also supports non-constant learning rates, which is different from existing literature. We establish convergence guarantees both in expectation and with high probability, demonstrating a complexity of $\mathcal{O}\left(\frac{m\sqrt{\bar{n}\ln{m}}}{\varepsilon}\right)$, where $\bar n$ is the average number of samples among $m$ groups. Remarkably, our approach outperforms the state-of-the-art method by a factor of $\sqrt{m}$. Furthermore, we extend our methodology to deal with the empirical minimax excess risk optimization (MERO) problem and manage to give the expectation bound and the high probability bound, accordingly. The complexity of our empirical MERO algorithm matches that of empirical GDRO at $\mathcal{O}\left(\frac{m\sqrt{\bar{n}\ln{m}}}{\varepsilon}\right)$, significantly surpassing the bounds of existing methods.

In this work, we propose an optimization framework for estimating a sparse robust one-dimensional subspace. Our objective is to minimize both the representation error and the penalty, in terms of the l1-norm criterion. Given that the problem is NP-hard, we introduce a linear relaxation-based approach. Additionally, we present a novel fitting procedure, utilizing simple ratios and sorting techniques. The proposed algorithm demonstrates a worst-case time complexity of $O(n^2 m \log n)$ and, in certain instances, achieves global optimality for the sparse robust subspace, thereby exhibiting polynomial time efficiency. Compared to extant methodologies, the proposed algorithm finds the subspace with the lowest discordance, offering a smoother trade-off between sparsity and fit. Its architecture affords scalability, evidenced by a 16-fold improvement in computational speeds for matrices of 2000x2000 over CPU version. Furthermore, this method is distinguished by several advantages, including its independence from initialization and deterministic and replicable procedures. Furthermore, this method is distinguished by several advantages, including its independence from initialization and deterministic and replicable procedures. The real-world example demonstrates the effectiveness of algorithm in achieving meaningful sparsity, underscoring its precise and useful application across various domains.

The Quadratic Assignment Problem (QAP) is one of the major domains in the field of evolutionary computation, and more widely in combinatorial optimization. This paper studies the phase transition of the QAP, which can be described as a dramatic change in the problem's computational complexity and satisfiability, within a narrow range of the problem parameters. To approach this phenomenon, we introduce a new QAP-SAT design of the initial problem based on submodularity to capture its difficulty with new features. This decomposition is studied experimentally using branch-and-bound and tabu search solvers. A phase transition parameter is then proposed. The critical parameter of phase transition satisfaction and that of the solving effort are shown to be highly correlated for tabu search, thus allowing the prediction of difficult instances.

The effectiveness of machine learning (ML) algorithms is deeply intertwined with the quality and diversity of their training datasets. Improved datasets, marked by superior quality, enhance the predictive accuracy and broaden the applicability of models across varied scenarios. Researchers often integrate data from multiple sources to mitigate biases and limitations of single-source datasets. However, this extensive data amalgamation raises significant ethical concerns, particularly regarding user privacy and the risk of unauthorized data disclosure. Various global legislative frameworks have been established to address these privacy issues. While crucial for safeguarding privacy, these regulations can complicate the practical deployment of ML technologies. Privacy-Preserving Machine Learning (PPML) addresses this challenge by safeguarding sensitive information, from health records to geolocation data, while enabling the secure use of this data in developing robust ML models. Within this realm, the Non-Readily Identifiable Data Collaboration (NRI-DC) framework emerges as an innovative approach, potentially resolving the 'data island' issue among institutions through non-iterative communication and robust privacy protections. However, in its current state, the NRI-DC framework faces model performance instability due to theoretical unsteadiness in creating collaboration functions. This study establishes a rigorous theoretical foundation for these collaboration functions and introduces new formulations through optimization problems on matrix manifolds and efficient solutions. Empirical analyses demonstrate that the proposed approach, particularly the formulation over orthogonal matrix manifolds, significantly enhances performance, maintaining consistency and efficiency without compromising communication efficiency or privacy protections.

This paper revisits a classical challenge in the design of stabilizing controllers for nonlinear systems with a norm-bounded input constraint. By extending Lin-Sontag's universal formula and introducing a generic (state-dependent) scaling term, a unifying controller design method is proposed. The incorporation of this generic scaling term gives a unified controller and enables the derivation of alternative universal formulas with various favorable properties, which makes it suitable for tailored control designs to meet specific requirements and provides versatility across different control scenarios. Additionally, we present a constructive approach to determine the optimal scaling term, leading to an explicit solution to an optimization problem, named optimization-based universal formula. The resulting controller ensures asymptotic stability, satisfies a norm-bounded input constraint, and optimizes a predefined cost function. Finally, the essential properties of the unified controllers are analyzed, including smoothness, continuity at the origin, stability margin, and inverse optimality. Simulations validate the approach, showcasing its effectiveness in addressing a challenging stabilizing control problem of a nonlinear system.

The Stochastic Gradient Descent method (SGD) and its stochastic variants have become methods of choice for solving finite-sum optimization problems arising from machine learning and data science thanks to their ability to handle large-scale applications and big datasets. In the last decades, researchers have made substantial effort to study the theoretical performance of SGD and its shuffling variants. However, only limited work has investigated its shuffling momentum variants, including shuffling heavy-ball momentum schemes for non-convex problems and Nesterov's momentum for convex settings. In this work, we extend the analysis of the shuffling momentum gradient method developed in [Tran et al (2021)] to both finite-sum convex and strongly convex optimization problems. We provide the first analysis of shuffling momentum-based methods for the strongly convex setting, attaining a convergence rate of $O(1/nT^2)$, where $n$ is the number of samples and $T$ is the number of training epochs. Our analysis is a state-of-the-art, matching the best rates of existing shuffling stochastic gradient algorithms in the literature.