Remote sensing images are highly valued for their ability to address complex real-world issues such as risk management, security, and meteorology. However, manually captioning these images is challenging and requires specialized knowledge across various domains. This letter presents an approach for automatically describing (captioning) remote sensing images. We propose a novel encoder-decoder setup that deploys a Text Graph Convolutional Network (TextGCN) and multi-layer LSTMs. The embeddings generated by TextGCN enhance the decoder's understanding by capturing the semantic relationships among words at both the sentence and corpus levels. Furthermore, we advance our approach with a comparison-based beam search method to ensure fairness in the search strategy for generating the final caption. We present an extensive evaluation of our approach against various other state-of-the-art encoder-decoder frameworks. We evaluated our method across three datasets using seven metrics: BLEU-1 to BLEU-4, METEOR, ROUGE-L, and CIDEr. The results demonstrate that our approach significantly outperforms other state-of-the-art encoder-decoder methods.

Recent research shows the susceptibility of machine learning models to adversarial attacks, wherein minor but maliciously chosen perturbations of the input can significantly degrade model performance. In this paper, we theoretically analyse the limits of robustness against such adversarial attacks in a nonparametric regression setting, by examining the minimax rates of convergence in an adversarial sup-norm. Our work reveals that the minimax rate under adversarial attacks in the input is the same as sum of two terms: one represents the minimax rate in the standard setting without adversarial attacks, and the other reflects the maximum deviation of the true regression function value within the target function class when subjected to the input perturbations. The optimal rates under the adversarial setup can be achieved by a plug-in procedure constructed from a minimax optimal estimator in the corresponding standard setting. Two specific examples are given to illustrate the established minimax results.

We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components. Assuming the factorization is known, we propose two model-based algorithms. The first one achieves minimax optimal regret guarantees for a rich class of factored structures, while the second one enjoys better computational complexity with a slightly worse regret. A key new ingredient of our algorithms is the design of a bonus term to guide exploration. We complement our algorithms by presenting several structure dependent lower bounds on regret for FMDPs that reveal the difficulty hiding in the intricacy of the structures.

High dimensional black-box optimization has broad applications but remains a challenging problem to solve. Given a set of samples xi, yi, building a global model (like Bayesian Optimization (BO)) suffers from the curse of dimensionality in the high-dimensional search space, while a greedy search may lead to sub-optimality. By recursively splitting the search space into regions with high/low function values, recent works like LaNAS shows good performance in Neural Architecture Search (NAS), reducing the sample complexity empirically. In this paper, we coin LA-MCTS that extends LaNAS to other domains. Unlike previous approaches, LA-MCTS learns the partition of the search space using a few samples and their function values in an online fashion.

The aim of this paper is to improve the understanding of the optimization landscape for policy optimization problems in reinforcement learning. Specifically, we show that the superlevel set of the objective function with respect to the policy parameter is always a connected set both in the tabular setting and under policies represented by a class of neural networks. In addition, we show that the optimization objective as a function of the policy parameter and reward satisfies a stronger "equiconnectedness" property. To our best knowledge, these are novel and previously unknown discoveries.We present an application of the connectedness of these superlevel sets to the derivation of minimax theorems for robust reinforcement learning. We show that any minimax optimization program which is convex on one side and is equiconnected on the other side observes the minimax equality (i.e. has a Nash equilibrium).

We propose a fully differentiable architecture for simultaneous semantic and instance segmentation (a.k.a. The latter solves a combinatorial optimization problem that elegantly incorporates semantic and boundary predictions to produce a panoptic labeling. Our formulation allows to directly maximize a smooth surrogate of the panoptic quality metric by backpropagating the gradient through the optimization problem. Experimental evaluation shows improvement by backpropagating through the optimization problem w.r.t. Overall, our approach of combinatorial optimization for panoptic segmentation (COPS) shows the utility of using optimization in tandem with deep learning in a challenging large scale real-world problem and showcases benefits and insights into training such an architecture.

Recent work on automated data augmentation strategies has led to state-of-the-art results in image classification and object detection. An obstacle to a large-scale adoption of these methods is that they require a separate and expensive search phase. A common way to overcome the expense of the search phase was to use a smaller proxy task. However, it was not clear if the optimized hyperparameters found on the proxy task are also optimal for the actual task. In this work, we rethink the process of designing automated data augmentation strategies.

Despite the success of generative adversarial networks (GANs) in generating visually appealing images, they are notoriously challenging to train. In order to stabilize the learning dynamics in minimax games, we propose a novel recursive reasoning algorithm: Level k Gradient Play (Lv. Our algorithm does not require sophisticated heuristics or second-order information, as do existing algorithms based on predictive updates. We show that as k increases, Lv. k GP converges asymptotically towards an accurate estimation of players' future strategy.Moreover, we justify that Lv. \infty GP naturally generalizes a line of provably convergent game dynamics which rely on predictive updates. Furthermore, we provide its local convergence property in nonconvex-nonconcave zero-sum games and global convergence in bilinear and quadratic games.

Planning enables autonomous agents to solve complex decision-making problems by evaluating predictions of the future. However, classical planning algorithms often become infeasible in real-world settings where state spaces are high-dimensional and transition dynamics unknown. The idea behind latent planning is to simplify the decision-making task by mapping it to a lower-dimensional embedding space. Common latent planning strategies are based on trajectory optimization techniques such as shooting or collocation, which are prone to failure in long-horizon and highly non-convex settings. In this work, we study long-horizon goal-reaching scenarios from visual inputs and formulate latent planning as an explorative tree search.

A recent Graph Neural Network (GNN) approach for learning to branch has been shown to successfully reduce the running time of branch-and-bound algorithms for Mixed Integer Linear Programming (MILP). While the GNN relies on a GPU for inference, MILP solvers are purely CPU-based. This severely limits its application as many practitioners may not have access to high-end GPUs. In this work, we ask two key questions. First, in a more realistic setting where only a CPU is available, is the GNN model still competitive?