Related papers: Resilient Multiple Choice Learning: A learned scor…
We consider the problem of learning a control policy that is robust against the parameter mismatches between the training environment and testing environment. We formulate this as a distributionally robust reinforcement learning (DR-RL)…
We study the problem of classification with selectively labeled data, whose distribution may differ from the full population due to historical decision-making. We exploit the fact that in many applications historical decisions were made by…
Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floating-point number independently, improving point estimates…
Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of long-range context through RNNLM rescoring with improved…
In the continual learning setting, tasks are encountered sequentially. The goal is to learn whilst i) avoiding catastrophic forgetting, ii) efficiently using model capacity, and iii) employing forward and backward transfer learning. In this…
Modular approaches that use a different composition of modules for each problem are a promising direction in continual learning (CL). However, searching through the large, discrete space of module compositions is challenging, especially…
Combining information from different sources is a common way to improve classification accuracy in Brain-Computer Interfacing (BCI). For instance, in small sample settings it is useful to integrate data from other subjects or sessions in…
Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by…
We tackle the problem of class incremental learning (CIL) in the realm of landcover classification from optical remote sensing (RS) images in this paper. The paradigm of CIL has recently gained much prominence given the fact that data are…
In-Context Learning (ICL) is a technique by which language models make predictions based on examples provided in their input context. Previously, their context window size imposed a limit on the number of examples that can be shown, making…
We study a class of constrained reinforcement learning (RL) problems in which multiple constraint specifications are not identified before training. It is challenging to identify appropriate constraint specifications due to the undefined…
Recent advancements in data-driven task-oriented dialogue systems (ToDs) struggle with incremental learning due to computational constraints and time-consuming issues. Continual Learning (CL) attempts to solve this by avoiding intensive…
This paper presents a novel ensemble learning approach called Residual Likelihood Forests (RLF). Our weak learners produce conditional likelihoods that are sequentially optimized using global loss in the context of previous learners within…
This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can…
Algorithm selection is commonly used to predict the best solver from a portfolio per per-instance. In many real scenarios, instances arrive in a stream: new instances become available over time, while the number of class labels can also…
A major challenge of reinforcement learning (RL) in real-world applications is the variation between environments, tasks or clients. Meta-RL (MRL) addresses this issue by learning a meta-policy that adapts to new tasks. Standard MRL methods…
Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events. To this end, we propose a novel multimodal framework that instantiates multiple instance…
In this paper, we propose a speaker verification method by an Attentive Multi-scale Convolutional Recurrent Network (AMCRN). The proposed AMCRN can acquire both local spatial information and global sequential information from the input…
Deep multi-view clustering has achieved remarkable progress but remains vulnerable to complex noise in real-world applications. Existing noisy robust methods predominantly rely on a simplified binary assumption, treating data as either…
Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing the Image-augmentation based Prediction consistency and…