13 papers
TEMPER: Tensorized Efficient Manifold-constrained Parameterization for Expressive Residual Routing
Yuxuan Gu, Wuyang Zhou, Huijun Xing +1
Residual connections rely on a static residual pathway, and are essential for training deep neural networks. Hyper-connections (HC) increase the expressivity of residual routing by…
Beyond Co-Movement: Locality by Exposures Enables a Joint Factor-Graph Framework for Portfolio Diversification
Sara Chehab, Giorgos Iacovides, Parisa Yazdanparast +1
Current portfolio construction methods are either agnostic to the effects of idiosyncratic shocks (standard factor models) or to the latent data structure driving systematic return…
FinSMART: Financial Sentiment Analysis for Algorithmic Trading through Market-Aligned Reinforcement Learning
Giorgos Iacovides, Wuyang Zhou, Danilo Mandic
Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs). However, existing approaches…
Tensorizing Engram: Sharing Latents Across N-Gram Embeddings is Beneficial in LLMs
Wuyang Zhou, Yuxuan Gu, Giorgos Iacovides +3
Modern language models represent text using discrete token-level embeddings, which forces recurring multi-token patterns to be learned implicitly across Transformer layers. Both Ov…
RefineBridge: Generative Bridge Models Improve Financial Forecasting by Foundation Models
Anthony Bolton, Wuyang Zhou, Zehua Chen +2
Financial time series forecasting is particularly challenging for transformer-based time series foundation models (TSFMs) due to non-stationarity, heavy-tailed distributions, and h…
KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices
Wuyang Zhou, Yuxuan Gu, Giorgos Iacovides +1
The success of Hyper-Connections (HC) in neural networks (NN) has also highlighted issues related to training instability and restricted scalability. The Manifold-Constrained Hyper…
TeRA: Vector-based Random Tensor Network for High-Rank Adaptation of Large Language Models
Yuxuan Gu, Wuyang Zhou, Giorgos Iacovides +1
Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), have significantly reduced the number of trainable parameters needed in fine-tuning large langua…
FinDPO: Financial Sentiment Analysis for Algorithmic Trading through Preference Optimization of LLMs
Giorgos Iacovides, Wuyang Zhou, Danilo Mandic
Opinions expressed in online finance-related textual data are having an increasingly profound impact on trading decisions and market movements. This trend highlights the vital role…
Understanding the Rank of Tensor Networks via an Intuitive Example-Driven Approach
Wuyang Zhou, Giorgos Iacovides, Kriton Konstantinidis +2
Tensor Network (TN) decompositions have emerged as an indispensable tool in Big Data analytics owing to their ability to provide compact low-rank representations, thus alleviating…
Domain-Aware Tensor Network Structure Search
Giorgos Iacovides, Wuyang Zhou, Chao Li +2
Tensor networks (TNs) provide efficient representations of high-dimensional data, yet identification of the optimal TN structures, the so called tensor network structure search (TN…
TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMs
Yuxuan Gu, Wuyang Zhou, Giorgos Iacovides +1
The reasoning abilities of Large Language Models (LLMs) can be improved by structurally denoising their weights, yet existing techniques primarily focus on denoising the feed-forwa…
Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection
Giorgos Iacovides, Wuyang Zhou, Danilo Mandic
We propose a novel framework that leverages large language models (LLMs) to guide the rank selection in tensor network models for higher-order data analysis. By utilising the intri…
Tensor Star Tensor Decomposition and Its Applications to Higher-order Compression and Completion
Wuyang Zhou, Yu-Bang Zheng, Qibin Zhao +1
A novel tensor decomposition framework, termed Tensor Star (TS) decomposition, is proposed which represents a new type of tensor network decomposition based on tensor contractions.…