Related papers: Context-Driven Performance Modeling for Causal Inf…
Transformer-based deep learning models are increasingly deployed on energy, and DRAM bandwidth constrained devices such as laptops and gaming consoles, which presents significant challenges in meeting the latency requirements of the models.…
Foundation Models (FMs) trained on Electronic Health Records (EHRs) have achieved state-of-the-art results on numerous clinical prediction tasks. However, most existing EHR FMs have context windows of <1k tokens. This prevents them from…
Mixture-of-Experts (MoE) models facilitate edge deployment by decoupling model capacity from active computation, yet their large memory footprint drives the need for GPU systems with near-data processing (NDP) capabilities that offload…
Long-context capability and computational efficiency are among the central challenges facing today's large language models. Existing efficient attention methods reduce computational complexity, but they typically suffer from a limited…
In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models (LLMs) significantly affects their performance in tasks demanding a high degree of context awareness, such as utilizing…
Concept bottleneck models (CBMs) are a class of interpretable neural network models that predict the target response of a given input based on its high-level concepts. Unlike the standard end-to-end models, CBMs enable domain experts to…
Hyperparameters play a critical role in machine learning. Hyperparameter tuning can make the difference between state-of-the-art and poor prediction performance for any algorithm, but it is particularly challenging for structure learning…
Context-dependent sequential decision making is commonly addressed either by providing context explicitly as an input or by increasing recurrent memory so that contextual information can be represented internally. We study a third…
Graphics processing units (GPUs) can improve deep neural network inference throughput via batch processing, where multiple tasks are concurrently processed. We focus on novel scenarios that the energy-constrained mobile devices offload…
Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Existing frameworks and compilers trade performance for…
The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of leveraging GPU parallelism. However, Transformers are computationally expensive at inference time,…
Neural conversational models tend to produce generic or safe responses in different contexts, e.g., reply \textit{"Of course"} to narrative statements or \textit{"I don't know"} to questions. In this paper, we propose an end-to-end approach…
Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where…
Causal inference is a fundamental research topic for discovering the cause-effect relationships in many disciplines. However, not all algorithms are equally well-suited for a given dataset. For instance, some approaches may only be able to…
In this work, we consider causal inference in various high-dimensional treatment settings, including for single multi-valued treatments and vector treatments with binary or continuous components, when the number of treatments can be…
Structural causal models are the basic modelling unit in Pearl's causal theory; in principle they allow us to solve counterfactuals, which are at the top rung of the ladder of causation. But they often contain latent variables that limit…
With the growing workload of inference tasks on mobile devices, state-of-the-art neural architectures (NAs) are typically designed through Neural Architecture Search (NAS) to identify NAs with good tradeoffs between accuracy and efficiency…
Cutting-edge embedded system applications, such as self-driving cars and unmanned drone software, are reliant on integrated CPU/GPU platforms for their DNNs-driven workload, such as perception and other highly parallel components. In this…
Causal inference has numerous real-world applications in many domains, such as health care, marketing, political science, and online advertising. Treatment effect estimation, a fundamental problem in causal inference, has been extensively…
Recent work has demonstrated that transformers and linear attention models can perform in-context learning (ICL) on simple function classes, such as linear regression. In this paper, we empirically study how these two attention mechanisms…