Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the subset practically performs on par with full data. When coreset selection is applied in realistic scenes, under the premise that the identified coreset has achieved comparable model performance, practitioners regularly desire the identified coreset can have a size as small as possible for lower costs and greater acceleration. Motivated by this desideratum, for the first time, we pose the problem of "coreset selection with prioritized multiple objectives", in which the smallest coreset size under model performance constraints is explored. Moreover, to address this problem, an innovative method is proposed, which maintains optimization priority order over the model performance and coreset size, and efficiently optimizes them in the coreset selection procedure. Theoretically, we provide the convergence guarantee of the proposed method. Empirically, extensive experiments confirm its superiority compared with previous strategies, often yielding better model performance with smaller coreset sizes.

We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of solving a sequence of optimization problems where the loss function changes per iteration. The common approach to solving this sequence of problems is to employ modern variants of the stochastic gradient descent algorithm such as Adam. These optimizers maintain their own internal parameters such as estimates of the first-order and the second-order moments of the gradient, and update them over time. Therefore, information obtained in previous iterations is used to solve the optimization problem in the current iteration. We demonstrate that this can contaminate the moment estimates because the optimization landscape can change arbitrarily from one iteration to the next one. To hedge against this negative effect, a simple idea is to reset the internal parameters of the optimizer when starting a new iteration. We empirically investigate this resetting idea by employing various optimizers in conjunction with the Rainbow algorithm. We demonstrate that this simple modification significantly improves the performance of deep RL on the Atari benchmark.

Estimating hyperparameters has been a long-standing problem in machine learning. We consider the case where the task at hand is modeled as the solution to an optimization problem. Here the exact gradient with respect to the hyperparameters cannot be feasibly computed and approximate strategies are required. We introduce a unified framework for computing hypergradients that generalizes existing methods based on the implicit function theorem and automatic differentiation/backpropagation, showing that these two seemingly disparate approaches are actually tightly connected. Our framework is extremely flexible, allowing its subproblems to be solved with any suitable method, to any degree of accuracy. We derive a priori and computable a posteriori error bounds for all our methods, and numerically show that our a posteriori bounds are usually more accurate. Our numerical results also show that, surprisingly, for efficient bilevel optimization, the choice of hypergradient algorithm is at least as important as the choice of lower-level solver.

Reinforcement Learning views the maximization of rewards and avoidance of punishments as central to explaining goal-directed behavior. However, over a life, organisms will need to learn about many different aspects of the world's structure: the states of the world and state-vector transition dynamics. The number of combinations of states grows exponentially as an agent incorporates new knowledge, and there is no obvious weighted combination of pre-existing rewards or costs defined for a given combination of states, as such a weighting would need to encode information about good and bad combinations prior to an agent's experience in the world. Therefore, we must develop more naturalistic accounts of behavior and motivation in large state-spaces. We show that it is possible to use only the intrinsic motivation metric of empowerment, which measures the agent's capacity to realize many possible futures under a transition operator. We propose to scale empowerment to hierarchical state-spaces by using Operator Bellman Equations. These equations produce state-time feasibility functions, which are compositional hierarchical state-time transition operators that map an initial state and time when an agent begins a policy to the final states and times of completing a goal. Because these functions are hierarchical operators we can define hierarchical empowerment measures on them. An agent can then optimize plans to distant states and times to maximize its hierarchical empowerment-gain, allowing it to discover goals that bring about a more favorable coupling of its internal structure (physiological states) to its external environment (world structure & spatial state). Life-long agents could therefore be primarily animated by principles of compositionality and empowerment, exhibiting self-concern for the growth & maintenance of their own structural integrity without recourse to reward-maximization.

We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in time, almost surely. Although Markovian policies are no longer sufficient, we show that there exist optimal deterministic policies augmented with cumulative costs. In fact, we present a fixed-parameter tractable reduction from anytime-constrained cMDPs to unconstrained MDPs. Our reduction yields planning and learning algorithms that are time and sample-efficient for tabular cMDPs so long as the precision of the costs is logarithmic in the size of the cMDP. However, we also show that computing non-trivial approximately optimal policies is NP-hard in general. To circumvent this bottleneck, we design provable approximation algorithms that efficiently compute or learn an arbitrarily accurate approximately feasible policy with optimal value so long as the maximum supported cost is bounded by a polynomial in the cMDP or the absolute budget. Given our hardness results, our approximation guarantees are the best possible under worst-case analysis.

Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator or not, for instance, to prove intellectual property theft. However, previous works are either limited to the closed-world setting or require undesirable changes to the generative model. We address these shortcomings by, first, viewing single-model attribution through the lens of anomaly detection. Arising from this change of perspective, we propose FLIPAD, a new approach for single-model attribution in the open-world setting based on final-layer inversion and anomaly detection. We show that the utilized final-layer inversion can be reduced to a convex lasso optimization problem, making our approach theoretically sound and computationally efficient. The theoretical findings are accompanied by an experimental study demonstrating the effectiveness of our approach and its flexibility to various domains.

We propose a novel methodology for forecasting spatio-temporal data using supervised semi-nonnegative matrix factorization (SSNMF) with frequency regularization. Matrix factorization is employed to decompose spatio-temporal data into spatial and temporal components. To improve clarity in the temporal patterns, we introduce a nonnegativity constraint on the time domain along with regularization in the frequency domain. Specifically, regularization in the frequency domain involves selecting features in the frequency space, making an interpretation in the frequency domain more convenient. We propose two methods in the frequency domain: soft and hard regularizations, and provide convergence guarantees to first-order stationary points of the corresponding constrained optimization problem. While our primary motivation stems from geophysical data analysis based on GRACE (Gravity Recovery and Climate Experiment) data, our methodology has the potential for wider application. Consequently, when applying our methodology to GRACE data, we find that the results with the proposed methodology are comparable to previous research in the field of geophysical sciences but offer clearer interpretability.

Metaheuristics have gained great success in academia and practice because their search logic can be applied to any problem with available solution representation, solution quality evaluation, and certain notions of locality. Manually designing metaheuristic algorithms for solving a target problem is criticized for being laborious, error-prone, and requiring intensive specialized knowledge. This gives rise to increasing interest in automated design of metaheuristic algorithms. With computing power to fully explore potential design choices, the automated design could reach and even surpass human-level design and could make high-performance algorithms accessible to a much wider range of researchers and practitioners. This paper presents a broad picture of automated design of metaheuristic algorithms, by conducting a survey on the common grounds and representative techniques in terms of design space, design strategies, performance evaluation strategies, and target problems in this field.

Multi-robot teams have attracted attention from industry and academia for their ability to perform collaborative tasks in unstructured environments, such as wilderness rescue and collaborative transportation.In this paper, we propose a trajectory planning method for a non-holonomic robotic team with collaboration in unstructured environments.For the adaptive state collaboration of a robot team to catch and transport targets to be rescued using a net, we model the process of catching the falling target with a net in a continuous and differentiable form.This enables the robot team to fully exploit the kinematic potential, thereby adaptively catching the target in an appropriate state.Furthermore, the size safety and topological safety of the net, resulting from the collaborative support of the robots, are guaranteed through geometric constraints.We integrate our algorithm on a car-like robot team and test it in simulations and real-world experiments to validate our performance.Our method is compared to state-of-the-art multi-vehicle trajectory planning methods, demonstrating significant performance in efficiency and trajectory quality.

This survey presents a comprehensive review of various methods and algorithms related to passing-through control of multi-robot systems in cluttered environments. Numerous studies have investigated this area, and we identify several avenues for enhancing existing methods. This survey describes some models of robots and commonly considered control objectives, followed by an in-depth analysis of four types of algorithms that can be employed for passing-through control: leader-follower formation control, multi-robot trajectory planning, control-based methods, and virtual tube planning and control. Furthermore, we conduct a comparative analysis of these techniques and provide some subjective and general evaluations.