We investigate the extent to which offline demonstration data can improve online learning. It is natural to expect some improvement, but the question is how, and by how much? We show that the degree of improvement must depend on the quality of the demonstration data. To generate portable insights, we focus on Thompson sampling (TS) applied to a multi-armed bandit as a prototypical online learning algorithm and model. The demonstration data is generated by an expert with a given competence level, a notion we introduce. We propose an informed TS algorithm that utilizes the demonstration data in a coherent way through Bayes' rule and derive a prior-dependent Bayesian regret bound. This offers insight into how pretraining can greatly improve online performance and how the degree of improvement increases with the expert's competence level. We also develop a practical, approximate informed TS algorithm through Bayesian bootstrapping and show substantial empirical regret reduction through experiments.
相關內容
In this paper, we improve the kernel alignment regret bound for online kernel learning in the regime of the Hinge loss function. Previous algorithm achieves a regret of $O((\mathcal{A}_TT\ln{T})^{\frac{1}{4}})$ at a computational complexity (space and per-round time) of $O(\sqrt{\mathcal{A}_TT\ln{T}})$, where $\mathcal{A}_T$ is called \textit{kernel alignment}. We propose an algorithm whose regret bound and computational complexity are better than previous results. Our results depend on the decay rate of eigenvalues of the kernel matrix. If the eigenvalues of the kernel matrix decay exponentially, then our algorithm enjoys a regret of $O(\sqrt{\mathcal{A}_T})$ at a computational complexity of $O(\ln^2{T})$. Otherwise, our algorithm enjoys a regret of $O((\mathcal{A}_TT)^{\frac{1}{4}})$ at a computational complexity of $O(\sqrt{\mathcal{A}_TT})$. We extend our algorithm to batch learning and obtain a $O(\frac{1}{T}\sqrt{\mathbb{E}[\mathcal{A}_T]})$ excess risk bound which improves the previous $O(1/\sqrt{T})$ bound.
Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. However, current LfD frameworks are not capable of fast adaptation to heterogeneous human demonstrations nor the large-scale deployment in ubiquitous robotics applications. In this paper, we propose a novel LfD framework, Fast Lifelong Adaptive Inverse Reinforcement learning (FLAIR). Our approach (1) leverages learned strategies to construct policy mixtures for fast adaptation to new demonstrations, allowing for quick end-user personalization, (2) distills common knowledge across demonstrations, achieving accurate task inference; and (3) expands its model only when needed in lifelong deployments, maintaining a concise set of prototypical strategies that can approximate all behaviors via policy mixtures. We empirically validate that FLAIR achieves adaptability (i.e., the robot adapts to heterogeneous, user-specific task preferences), efficiency (i.e., the robot achieves sample-efficient adaptation), and scalability (i.e., the model grows sublinearly with the number of demonstrations while maintaining high performance). FLAIR surpasses benchmarks across three control tasks with an average 57% improvement in policy returns and an average 78% fewer episodes required for demonstration modeling using policy mixtures. Finally, we demonstrate the success of FLAIR in a table tennis task and find users rate FLAIR as having higher task (p<.05) and personalization (p<.05) performance.
Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A parameter-efficient adaptation method suggests training an adapter for each domain on the task of language modeling. This leads to good in-domain scores but can be impractical for domain- or resource-restricted settings. A solution is to use a related-domain adapter for the novel domain at test time. In this paper, we introduce AdapterSoup, an approach that performs weight-space averaging of adapters trained on different domains. Our approach is embarrassingly parallel: first, we train a set of domain-specific adapters; then, for each novel domain, we determine which adapters should be averaged at test time. We present extensive experiments showing that AdapterSoup consistently improves performance to new domains without extra training. We also explore weight averaging of adapters trained on the same domain with different hyper-parameters, and show that it preserves the performance of a PLM on new domains while obtaining strong in-domain results. We explore various approaches for choosing which adapters to combine, such as text clustering and semantic similarity. We find that using clustering leads to the most competitive results on novel domains.
This paper proposes a computational framework for the design optimization of stable structures under large deformations by incorporating nonlinear buckling constraints. A novel strategy for suppressing spurious buckling modes related to low-density elements is proposed. The strategy depends on constructing a pseudo-mass matrix that assigns small pseudo masses for DOFs surrounded by only low-density elements and degenerates to an identity matrix for the solid region. A novel optimization procedure is developed that can handle both simple and multiple eigenvalues wherein consistent sensitivities of simple eigenvalues and directional derivatives of multiple eigenvalues are derived and utilized in a gradient-based optimization algorithm - the method of moving asymptotes. An adaptive linear energy interpolation method is also incorporated in nonlinear analyses to handle the low-density elements distortion under large deformations. The numerical results demonstrate that, for systems with either low or high symmetries, the nonlinear stability constraints can ensure structural stability at the target load under large deformations. Post-analysis on the B-spline fitted designs shows that the safety margin, i.e., the gap between the target load and the 1st critical load, of the optimized structures can be well controlled by selecting different stability constraint values. Interesting structural behaviors such as mode switching and multiple bifurcations are also demonstrated.
Large language models (LLMs), such as GPT-3 and ChatGPT, have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning, which involves inference based on a few demonstration examples. Despite their successes in NLP tasks, no investigation has been conducted to assess the ability of LLMs to perform document information extraction (DIE) using in-context learning. Applying LLMs to DIE poses two challenges: the modality and task gap. To this end, we propose a simple but effective in-context learning framework called ICL-D3IE, which enables LLMs to perform DIE with different types of demonstration examples. Specifically, we extract the most difficult and distinct segments from hard training documents as hard demonstrations for benefiting all test instances. We design demonstrations describing relationships that enable LLMs to understand positional relationships. We introduce formatting demonstrations for easy answer extraction. Additionally, the framework improves diverse demonstrations by updating them iteratively. Our experiments on three widely used benchmark datasets demonstrate that the ICL-D3IE framework enables GPT-3/ChatGPT to achieve superior performance when compared to previous pre-trained methods fine-tuned with full training in both the in-distribution (ID) setting and in the out-of-distribution (OOD) setting.
Intelligent manufacturing is becoming increasingly important due to the growing demand for maximizing productivity and flexibility while minimizing waste and lead times. This work investigates automated secondary robotic food packaging solutions that transfer food products from the conveyor belt into containers. A major problem in these solutions is varying product supply which can cause drastic productivity drops. Conventional rule-based approaches, used to address this issue, are often inadequate, leading to violation of the industry's requirements. Reinforcement learning, on the other hand, has the potential of solving this problem by learning responsive and predictive policy, based on experience. However, it is challenging to utilize it in highly complex control schemes. In this paper, we propose a reinforcement learning framework, designed to optimize the conveyor belt speed while minimizing interference with the rest of the control system. When tested on real-world data, the framework exceeds the performance requirements (99.8% packed products) and maintains quality (100% filled boxes). Compared to the existing solution, our proposed framework improves productivity, has smoother control, and reduces computation time.
It is important to quantify the uncertainty of input samples, especially in mission-critical domains such as autonomous driving and healthcare, where failure predictions on out-of-distribution (OOD) data are likely to cause big problems. OOD detection problem fundamentally begins in that the model cannot express what it is not aware of. Post-hoc OOD detection approaches are widely explored because they do not require an additional re-training process which might degrade the model's performance and increase the training cost. In this study, from the perspective of neurons in the deep layer of the model representing high-level features, we introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data. We propose a novel method, Leveraging Important Neurons (LINe), for post-hoc Out of distribution detection. Shapley value-based pruning reduces the effects of noisy outputs by selecting only high-contribution neurons for predicting specific classes of input data and masking the rest. Activation clipping fixes all values above a certain threshold into the same value, allowing LINe to treat all the class-specific features equally and just consider the difference between the number of activated feature differences between in-distribution and OOD data. Comprehensive experiments verify the effectiveness of the proposed method by outperforming state-of-the-art post-hoc OOD detection methods on CIFAR-10, CIFAR-100, and ImageNet datasets.
Label noise poses a serious threat to deep neural networks (DNNs). Employing robust loss function which reconciles fitting ability with robustness is a simple but effective strategy to handle this problem. However, the widely-used static trade-off between these two factors contradicts the dynamic nature of DNNs learning with label noise, leading to inferior performance. Therefore, we propose a dynamics-aware loss (DAL) to solve this problem. Considering that DNNs tend to first learn generalized patterns, then gradually overfit label noise, DAL strengthens the fitting ability initially, then gradually increases the weight of robustness. Moreover, at the later stage, we let DNNs put more emphasis on easy examples which are more likely to be correctly labeled than hard ones and introduce a bootstrapping term to further reduce the negative impact of label noise. Both the detailed theoretical analyses and extensive experimental results demonstrate the superiority of our method.
Class-incremental continual learning is a core step towards developing artificial intelligence systems that can continuously adapt to changes in the environment by learning new concepts without forgetting those previously learned. This is especially needed in the medical domain where continually learning from new incoming data is required to classify an expanded set of diseases. In this work, we focus on how old knowledge can be leveraged to learn new classes without catastrophic forgetting. We propose a framework that comprises of two main components: (1) a dynamic architecture with expanding representations to preserve previously learned features and accommodate new features; and (2) a training procedure alternating between two objectives to balance the learning of new features while maintaining the model's performance on old classes. Experiment results on multiple medical datasets show that our solution is able to achieve superior performance over state-of-the-art baselines in terms of class accuracy and forgetting.
While existing work in robust deep learning has focused on small pixel-level $\ell_p$ norm-based perturbations, this may not account for perturbations encountered in several real world settings. In many such cases although test data might not be available, broad specifications about the types of perturbations (such as an unknown degree of rotation) may be known. We consider a setup where robustness is expected over an unseen test domain that is not i.i.d. but deviates from the training domain. While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes. We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space, without having access to the data from the test domain. Our adversarial training solves a min-max optimization problem, with the inner maximization generating adversarial perturbations, and the outer minimization finding model parameters by optimizing the loss on adversarial perturbations generated from the inner maximization. We demonstrate the applicability of our approach on three types of naturally occurring perturbations -- object-related shifts, geometric transformations, and common image corruptions. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations. We demonstrate the usefulness of the proposed approach by showing the robustness gains of deep neural networks trained using our adversarial training on MNIST, CIFAR-10, and a new variant of the CLEVR dataset.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191