We study a constructive algorithm that approximates Gateaux derivatives for statistical functionals by finite differencing, with a focus on functionals that arise in causal inference. We study the case where probability distributions are not known a priori but need to be estimated from data. These estimated distributions lead to empirical Gateaux derivatives, and we study the relationships between empirical, numerical, and analytical Gateaux derivatives. Starting with a case study of the interventional mean (average potential outcome), we delineate the relationship between finite differences and the analytical Gateaux derivative. We then derive requirements on the rates of numerical approximation in perturbation and smoothing that preserve the statistical benefits of one-step adjustments, such as rate double robustness. We then study more complicated functionals such as dynamic treatment regimes, the linear-programming formulation for policy optimization in infinite-horizon Markov decision processes, and sensitivity analysis in causal inference. More broadly, we study optimization-based estimators, since this begets a class of estimands where identification via regression adjustment is straightforward but obtaining influence functions under minor variations thereof is not. The ability to approximate bias adjustments in the presence of arbitrary constraints illustrates the usefulness of constructive approaches for Gateaux derivatives. We also find that the statistical structure of the functional (rate double robustness) can permit less conservative rates for finite-difference approximation. This property, however, can be specific to particular functionals; e.g., it occurs for the average potential outcome (hence average treatment effect) but not the infinite-horizon MDP policy value.

In digital online advertising, advertisers procure ad impressions simultaneously on multiple platforms, or so-called channels, such as Google Ads, Meta Ads Manager, etc., each of which consists of numerous ad auctions. We study how an advertiser maximizes total conversion (e.g. ad clicks) while satisfying aggregate return-on-investment (ROI) and budget constraints across all channels. In practice, an advertiser does not have control over, and thus cannot globally optimize, which individual ad auctions she participates in for each channel, and instead authorizes a channel to procure impressions on her behalf: the advertiser can only utilize two levers on each channel, namely setting a per-channel budget and per-channel target ROI. In this work, we first analyze the effectiveness of each of these levers for solving the advertiser's global multi-channel problem. We show that when an advertiser only optimizes over per-channel ROIs, her total conversion can be arbitrarily worse than what she could have obtained in the global problem. Further, we show that the advertiser can achieve the global optimal conversion when she only optimizes over per-channel budgets. In light of this finding, under a bandit feedback setting that mimics real-world scenarios where advertisers have limited information on ad auctions in each channels and how channels procure ads, we present an efficient learning algorithm that produces per-channel budgets whose resulting conversion approximates that of the global optimal problem. Finally, we argue that all our results hold for both single-item and multi-item auctions from which channels procure impressions on advertisers' behalf.

The agricultural sector currently faces significant challenges in water resource conservation and crop yield optimization, primarily due to concerns over freshwater scarcity. Traditional irrigation scheduling methods often prove inadequate in meeting the needs of large-scale irrigation systems. To address this issue, this paper proposes a predictive irrigation scheduler that leverages the three paradigms of machine learning to optimize irrigation schedules. The proposed scheduler employs the k-means clustering approach to divide the field into distinct irrigation management zones based on soil hydraulic parameters and topology information. Furthermore, a long short-term memory network is employed to develop dynamic models for each management zone, enabling accurate predictions of soil moisture dynamics. Formulated as a mixed-integer model predictive control problem, the scheduler aims to maximize water uptake while minimizing overall water consumption and irrigation costs. To tackle the mixed-integer optimization challenge, the proximal policy optimization algorithm is utilized to train a reinforcement learning agent responsible for making daily irrigation decisions. To evaluate the performance of the proposed scheduler, a 26.4-hectare field in Lethbridge, Canada, was chosen as a case study for the 2015 and 2022 growing seasons. The results demonstrate the superiority of the proposed scheduler compared to a traditional irrigation scheduling method in terms of water use efficiency and crop yield improvement for both growing seasons. Notably, the proposed scheduler achieved water savings ranging from 6.4% to 22.8%, along with yield increases ranging from 2.3% to 4.3%.

In the rank-constrained optimization problem (RCOP), it minimizes a linear objective function over a prespecified closed rank-constrained domain set and $m$ generic two-sided linear matrix inequalities. Motivated by the Dantzig-Wolfe (DW) decomposition, a popular approach of solving many nonconvex optimization problems, we investigate the strength of DW relaxation (DWR) of the RCOP, which admits the same formulation as RCOP except replacing the domain set by its closed convex hull. Notably, our goal is to characterize conditions under which the DWR matches RCOP for any m two-sided linear matrix inequalities. From the primal perspective, we develop the first-known simultaneously necessary and sufficient conditions that achieve: (i) extreme point exactness -- all the extreme points of the DWR feasible set belong to that of the RCOP; (ii) convex hull exactness -- the DWR feasible set is identical to the closed convex hull of RCOP feasible set; and (iii) objective exactness -- the optimal values of the DWR and RCOP coincide. The proposed conditions unify, refine, and extend the existing exactness results in the quadratically constrained quadratic program (QCQP) and fair unsupervised learning. These conditions can be very useful to identify new results, including the extreme point exactness for a QCQP problem that admits an inhomogeneous objective function with two homogeneous two-sided quadratic constraints and the convex hull exactness for fair SVD.

We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training. By examining the underlying high-dimensional probabilistic models, we reveal that the training process explores an effectively low-dimensional manifold. Networks with a wide range of architectures, sizes, trained using different optimization methods, regularization techniques, data augmentation techniques, and weight initializations lie on the same manifold in the prediction space. We study the details of this manifold to find that networks with different architectures follow distinguishable trajectories but other factors have a minimal influence; larger networks train along a similar manifold as that of smaller networks, just faster; and networks initialized at very different parts of the prediction space converge to the solution along a similar manifold.

This paper presents a fully decentralized approach for realtime non-cooperative multi-robot navigation in social mini-games, such as navigating through a narrow doorway or negotiating right of way at a corridor intersection. Our contribution is a new realtime bi-level optimization algorithm, in which the top-level optimization consists of computing a fair and collision-free ordering followed by the bottom-level optimization which plans optimal trajectories conditioned on the ordering. We show that, given such a priority order, we can impose simple kinodynamic constraints on each robot that are sufficient for it to plan collision-free trajectories with minimal deviation from their preferred velocities, similar to how humans navigate in these scenarios. We successfully deploy the proposed algorithm in the real world using F$1/10$ robots, a Clearpath Jackal, and a Boston Dynamics Spot as well as in simulation using the SocialGym 2.0 multi-agent social navigation simulator, in the doorway and corridor intersection scenarios. We compare with state-of-the-art social navigation methods using multi-agent reinforcement learning, collision avoidance algorithms, and crowd simulation models. We show that $(i)$ classical navigation performs $44\%$ better than the state-of-the-art learning-based social navigation algorithms, $(ii)$ without a scheduling protocol, our approach results in collisions in social mini-games $(iii)$ our approach yields $2\times$ and $5\times$ fewer velocity changes than CADRL in doorways and intersections, and finally $(iv)$ bi-level navigation in doorways at a flow rate of $2.8 - 3.3$ (ms)$^{-1}$ is comparable to flow rate in human navigation at a flow rate of $4$ (ms)$^{-1}$.

Quantum computing has developed significantly in recent years. Developing algorithms to estimate various metrics for SQL queries has been an important research question in database research since the estimations affect query optimization and database performance. This work represents a quantum natural language processing (QNLP) -inspired approach for constructing a quantum machine learning model which can classify SQL queries with respect to their execution times and cardinalities. From the quantum machine learning perspective, we compare our model and results to the previous research in QNLP and conclude that our model reaches similar accuracy as the QNLP model in the classification tasks. This indicates that the QNLP model is a promising method even when applied to problems that are not in QNLP. We study the developed quantum machine learning model by calculating its expressibility and entangling capability histograms. The results show that the model has favorable properties to be expressible but also not too complex to be executed on quantum hardware.

Optimizing building configurations for an efficient use of energy is increasingly receiving attention by current research and several methods have been developed to address this task. Selecting a suitable configuration based on multiple conflicting objectives, such as initial investment cost, recurring cost, robustness with respect to uncertainty of grid operation is, however, a difficult multi-criteria decision making problem. Concept identification can facilitate a decision maker by sorting configuration options into semantically meaningful groups (concepts), further introducing constraints to meet trade-off expectations for a selection of objectives. In this study, for a set of 20000 Pareto-optimal building energy management configurations, resulting from a many-objective evolutionary optimization, multiple concept identification iterations are conducted to provide a basis for making an informed investment decision. In a series of subsequent analysis steps, it is shown how the choice of description spaces, i.e., the partitioning of the features into sets for which consistent and non-overlapping concepts are required, impacts the type of information that can be extracted and that different setups of description spaces illuminate several different aspects of the configuration data - an important aspect that has not been addressed in previous work.

We consider (stochastic) subgradient methods for strongly convex but potentially nonsmooth non-Lipschitz optimization. We provide new equivalent dual descriptions (in the style of dual averaging) for the classic subgradient method, the proximal subgradient method, and the switching subgradient method. These equivalences enable $O(1/T)$ convergence guarantees in terms of both their classic primal gap and a not previously analyzed dual gap for strongly convex optimization. Consequently, our theory provides these classic methods with simple, optimal stopping criteria and optimality certificates at no added computational cost. Our results apply under nearly any stepsize selection and for a range of non-Lipschitz ill-conditioned problems where the early iterations of the subgradient method may diverge exponentially quickly (a phenomenon which, to the best of our knowledge, no prior works address). Even in the presence of such undesirable behaviors, our theory still ensures and bounds eventual convergence.

We propose a new method for optimistic planning in infinite-horizon discounted Markov decision processes based on the idea of adding regularization to the updates of an otherwise standard approximate value iteration procedure. This technique allows us to avoid contraction and monotonicity arguments typically required by existing analyses of approximate dynamic programming methods, and in particular to use approximate transition functions estimated via least-squares procedures in MDPs with linear function approximation. We use our method to recover known guarantees in tabular MDPs and to provide a computationally efficient algorithm for learning near-optimal policies in discounted linear mixture MDPs from a single stream of experience, and show it achieves near-optimal statistical guarantees.