长尾数据集（Head Class）组成的培训样本比尾巴类别多得多，这会导致识别模型对头等舱有偏见。加权损失是缓解此问题的最受欢迎的方法之一，最近的一项工作表明，班级难度可能比常规使用的类频率更好地决定了权重的分布。在先前的工作中使用了一种启发式公式来量化难度，但是我们从经验上发现，最佳公式取决于数据集的特征。因此，我们提出了困难网络，该难题学习在元学习框架中使用模型的性能来预测类的难度。为了使其在其他班级的背景下学习班级的合理难度，我们新介绍了两个关键概念，即相对难度和驾驶员损失。前者有助于困难网络在计算班级难度时考虑其他课程，而后者对于将学习指向有意义的方向是必不可少的。对流行的长尾数据集进行了广泛的实验证明了该方法的有效性，并且在多个长尾数据集上实现了最先进的性能。

与其他类别（称为少数族裔或尾巴类）相比，很少的类或类别（称为多数或头等类别的类别）具有更高的数据样本数量，在现实世界中，长尾数据集经常遇到。在此类数据集上培训深层神经网络会给质量级别带来偏见。到目前为止，研究人员提出了多种加权损失和数据重新采样技术，以减少偏见。但是，大多数此类技术都认为，尾巴类始终是最难学习的类，因此需要更多的重量或注意力。在这里，我们认为该假设可能并不总是成立的。因此，我们提出了一种新颖的方法，可以在模型的训练阶段动态测量每个类别的瞬时难度。此外，我们使用每个班级的难度度量来设计一种新型的加权损失技术，称为“基于阶级难度的加权（CDB-W）损失”和一种新型的数据采样技术，称为“基于类别难度的采样）（CDB-S ）'。为了验证CDB方法的广泛可用性，我们对多个任务进行了广泛的实验，例如图像分类，对象检测，实例分割和视频操作分类。结果验证了CDB-W损失和CDB-S可以在许多类似于现实世界中用例的类别不平衡数据集（例如Imagenet-LT，LVIS和EGTEA）上实现最先进的结果。

and widely used information measurement metric, particularly popularized for SSVEP- based Brain-Computer (BCI) interfaces. By combining speed and accuracy into a single-valued parameter, this metric aids in the evaluation and comparison of various target identification algorithms across different BCI communities. To accurately depict performance and inspire an end-to-end design for futuristic BCI designs, a more thorough examination and definition of ITR is therefore required. We model the symbiotic communication medium, hosted by the retinogeniculate visual pathway, as a discrete memoryless channel and use the modified capacity expressions to redefine the ITR. We use graph theory to characterize the relationship between the asymmetry of the transition statistics and the ITR gain with the new definition, leading to potential bounds on data rate performance. On two well-known SSVEP datasets, we compared two cutting-edge target identification methods. Results indicate that the induced DM channel asymmetry has a greater impact on the actual perceived ITR than the change in input distribution. Moreover, it is demonstrated that the ITR gain under the new definition is inversely correlated with the asymmetry in the channel transition statistics. Individual input customizations are further shown to yield perceived ITR performance improvements. An algorithm is proposed to find the capacity of binary classification and further discussions are given to extend such results to ensemble techniques.We anticipate that the results of our study will contribute to the characterization of the highly dynamic BCI channel capacities, performance thresholds, and improved BCI stimulus designs for a tighter symbiosis between the human brain and computer systems while enhancing the efficiency of the underlying communication resources.

Learning policies from fixed offline datasets is a key challenge to scale up reinforcement learning (RL) algorithms towards practical applications. This is often because off-policy RL algorithms suffer from distributional shift, due to mismatch between dataset and the target policy, leading to high variance and over-estimation of value functions. In this work, we propose variance regularization for offline RL algorithms, using stationary distribution corrections. We show that by using Fenchel duality, we can avoid double sampling issues for computing the gradient of the variance regularizer. The proposed algorithm for offline variance regularization (OVAR) can be used to augment any existing offline policy optimization algorithms. We show that the regularizer leads to a lower bound to the offline policy optimization objective, which can help avoid over-estimation errors, and explains the benefits of our approach across a range of continuous control domains when compared to existing state-of-the-art algorithms.

When testing conditions differ from those represented in training data, so-called out-of-distribution (OOD) inputs can mar the reliability of black-box learned components in the modern robot autonomy stack. Therefore, coping with OOD data is an important challenge on the path towards trustworthy learning-enabled open-world autonomy. In this paper, we aim to demystify the topic of OOD data and its associated challenges in the context of data-driven robotic systems, drawing connections to emerging paradigms in the ML community that study the effect of OOD data on learned models in isolation. We argue that as roboticists, we should reason about the overall system-level competence of a robot as it performs tasks in OOD conditions. We highlight key research questions around this system-level view of OOD problems to guide future research toward safe and reliable learning-enabled autonomy.

Lifelong learning aims to create AI systems that continuously and incrementally learn during a lifetime, similar to biological learning. Attempts so far have met problems, including catastrophic forgetting, interference among tasks, and the inability to exploit previous knowledge. While considerable research has focused on learning multiple input distributions, typically in classification, lifelong reinforcement learning (LRL) must also deal with variations in the state and transition distributions, and in the reward functions. Modulating masks, recently developed for classification, are particularly suitable to deal with such a large spectrum of task variations. In this paper, we adapted modulating masks to work with deep LRL, specifically PPO and IMPALA agents. The comparison with LRL baselines in both discrete and continuous RL tasks shows competitive performance. We further investigated the use of a linear combination of previously learned masks to exploit previous knowledge when learning new tasks: not only is learning faster, the algorithm solves tasks that we could not otherwise solve from scratch due to extremely sparse rewards. The results suggest that RL with modulating masks is a promising approach to lifelong learning, to the composition of knowledge to learn increasingly complex tasks, and to knowledge reuse for efficient and faster learning.

Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Most targeted syntactic evaluation datasets ask models to make these judgements with just a single context-free sentence as input. This does not match language models' training regime, in which input sentences are always highly contextualized by the surrounding corpus. This mismatch raises an important question: how robust are models' syntactic judgements in different contexts? In this paper, we investigate the stability of language models' performance on targeted syntactic evaluations as we vary properties of the input context: the length of the context, the types of syntactic phenomena it contains, and whether or not there are violations of grammaticality. We find that model judgements are generally robust when placed in randomly sampled linguistic contexts. However, they are substantially unstable for contexts containing syntactic structures matching those in the critical test content. Among all tested models (GPT-2 and five variants of OPT), we significantly improve models' judgements by providing contexts with matching syntactic structures, and conversely significantly worsen them using unacceptable contexts with matching but violated syntactic structures. This effect is amplified by the length of the context, except for unrelated inputs. We show that these changes in model performance are not explainable by simple features matching the context and the test inputs, such as lexical overlap and dependency overlap. This sensitivity to highly specific syntactic features of the context can only be explained by the models' implicit in-context learning abilities.

Recent advancements in sensing and communication facilitate obtaining high-frequency real-time data from various physical systems like power networks, climate systems, biological networks, etc. However, since the data are recorded by physical sensors, it is natural that the obtained data is corrupted by measurement noise. In this paper, we present a novel algorithm for online real-time learning of dynamical systems from noisy time-series data, which employs the Robust Koopman operator framework to mitigate the effect of measurement noise. The proposed algorithm has three main advantages: a) it allows for online real-time monitoring of a dynamical system; b) it obtains a linear representation of the underlying dynamical system, thus enabling the user to use linear systems theory for analysis and control of the system; c) it is computationally fast and less intensive than the popular Extended Dynamic Mode Decomposition (EDMD) algorithm. We illustrate the efficiency of the proposed algorithm by applying it to identify the Van der Pol oscillator, the IEEE 68 bus system, and a ring network of Van der Pol oscillators.

ML-based motion planning is a promising approach to produce agents that exhibit complex behaviors, and automatically adapt to novel environments. In the context of autonomous driving, it is common to treat all available training data equally. However, this approach produces agents that do not perform robustly in safety-critical settings, an issue that cannot be addressed by simply adding more data to the training set - we show that an agent trained using only a 10% subset of the data performs just as well as an agent trained on the entire dataset. We present a method to predict the inherent difficulty of a driving situation given data collected from a fleet of autonomous vehicles deployed on public roads. We then demonstrate that this difficulty score can be used in a zero-shot transfer to generate curricula for an imitation-learning based planning agent. Compared to training on the entire unbiased training dataset, we show that prioritizing difficult driving scenarios both reduces collisions by 15% and increases route adherence by 14% in closed-loop evaluation, all while using only 10% of the training data.

We propose a learning-based robust predictive control algorithm that compensates for significant uncertainty in the dynamics for a class of discrete-time systems that are nominally linear with an additive nonlinear component. Such systems commonly model the nonlinear effects of an unknown environment on a nominal system. We optimize over a class of nonlinear feedback policies inspired by certainty equivalent "estimate-and-cancel" control laws pioneered in classical adaptive control to achieve significant performance improvements in the presence of uncertainties of large magnitude, a setting in which existing learning-based predictive control algorithms often struggle to guarantee safety. In contrast to previous work in robust adaptive MPC, our approach allows us to take advantage of structure (i.e., the numerical predictions) in the a priori unknown dynamics learned online through function approximation. Our approach also extends typical nonlinear adaptive control methods to systems with state and input constraints even when we cannot directly cancel the additive uncertain function from the dynamics. We apply contemporary statistical estimation techniques to certify the system's safety through persistent constraint satisfaction with high probability. Moreover, we propose using Bayesian meta-learning algorithms that learn calibrated model priors to help satisfy the assumptions of the control design in challenging settings. Finally, we show in simulation that our method can accommodate more significant unknown dynamics terms than existing methods and that the use of Bayesian meta-learning allows us to adapt to the test environments more rapidly.