10 accepted papers
Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the robustness of the vision-language models. Different from the vanil
Learning universal representations for time series is fundamental for diverse downstream tasks. However, current approaches largely rely on handcrafted data augmentations, which may distort intrinsic temporal dynamics and structural regularities. In addition, most static representation learning fram
Large vision-language models (LVLMs) have demonstrated remarkable capabilities in understanding multimodal data such as images and text. However, the number of visual tokens in these models often far exceeds that of textual tokens, resulting in substantial redundancy and high inference costs. Existi
This paper proposes two linear projection approaches for supervised dimension reduction using only the first and second-order statistics for the binary classification problem. They are derived under the general Gaussian model by maximizing the Kullback-Leibler divergence between the two classes in t…
Implicit neural representations (INRs) have demonstrated their effectiveness in continuous modeling for image signals. However, INRs typically operate in a continuous space, which makes it difficult to integrate the discrete symbols and structures inherent in human language. Despite this, text featu…
This paper focuses on performance analysis of linkage-based hierarchical agglomerative clustering algorithms for sequence clustering using the Kolmogrov-Smirnov distance. Data sequences are assumed to be generated from unknown continuous distributions. The goal is to group the data sequences whose u…
We characterize the asymptotic performance of nonparametric goodness of fit testing. The exponential decay rate of the type-II error probability is used as the asymptotic performance metric, and a test is optimal if it achieves the maximum rate subject to a constant level constraint on the type-I er…
This paper studies clustering using a Kolmogorov-Smirnov based K-means algorithm. All data sequences are assumed to be generated by unknown continuous distributions. The pairwise KS distances of the distributions are assumed to be lower bounded by a certain positive constant. The convergence analysi…
This paper considers the problem of constructing 2-D room shape. A mobile device with co-located microphone and loudspeaker is used and the distances between consecutive measurement points are assumed to be known. The uniqueness of the mapping between the first-order echoes and the room geometry is…
This paper considers multi-agent distributed optimization with quantized communication which is needed when inter-agent communications are subject to finite capacity and other practical constraints. To minimize the global objective formed by a sum of local convex functions, we develop a quantized di…