相关论文: HyperINF: Unleashing the HyperPower of the Schulz'…

Identifying key influencers from time series data without a known prior network structure is a challenging problem in various applications, from crime analysis to social media. While much work has focused on event-based time series…

Large number of weights in deep neural networks makes the models difficult to be deployed in low memory environments such as, mobile phones, IOT edge devices as well as "inferencing as a service" environments on cloud. Prior work has…

This work presents a novel matrix-based method for constructing an approximation Hessian using only function evaluations. The method requires less computational power than interpolation-based methods and is easy to implement in matrix-based…

With the advancement of large language models (LLMs), solving complex reasoning tasks has gained increasing attention. Inference-time computation methods (e.g., Best-of-N, beam search, et al.) are particularly valuable as they can enhance…

Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only…

Inspired by recent work on learning with distribution shift, we give a general outlier removal algorithm called iterative polynomial filtering and show a number of striking applications for supervised learning with contamination: (1) We…

The presence of missing values within high-dimensional data is an ubiquitous problem for many applied sciences. A serious limitation of many available data mining and machine learning methods is their inability to handle partially missing…

Influence Maximization problem has received significant attention in recent years due to its application in various do?mains such as product recommendation, public opinion dissemination, and disease propagation. This paper proposes a…

This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key principle underlying the design of PowerInfer is exploiting the high…

Likelihood-free Bayesian inference algorithms are popular methods for calibrating the parameters of complex, stochastic models, required when the likelihood of the observed data is intractable. These algorithms characteristically rely…

Motivated by the growing interest in quantum machine learning, in particular quantum neural networks (QNNs), we study how recently introduced evaluation metrics based on the Fisher information matrix (FIM) are effective for predicting their…

We propose a supervised learning algorithm for machine learning applications. Contrary to the model developing in the classical methods, which treat training, validation, and test as separate steps, in the presented approach, there is a…

General-purpose open-domain dense retrieval systems are usually trained with a large, eclectic mix of corpora and search tasks. How should these diverse corpora and tasks be sampled for training? Conventional approaches sample them…

The Fisher information matrix (FIM) has long been of interest in statistics and other areas. It is widely used to measure the amount of information and calculate the lower bound for the variance for maximum likelihood estimation (MLE). In…

While numerous defense methods have been proposed to prohibit potential poisoning attacks from untrusted data sources, most research works only defend against specific attacks, which leaves many avenues for an adversary to exploit. In this…

To fully leverage the advantages of large-scale pre-trained language models (PLMs) on downstream tasks, it has become a ubiquitous adaptation paradigm to fine-tune the entire parameters of PLMs. However, this paradigm poses issues of…

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…

Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied…

The past several years have witnessed the success of transformer-based models, and their scale and application scenarios continue to grow aggressively. The current landscape of transformer models is increasingly diverse: the model size…

Gradient-based data attribution methods, such as influence functions, are critical for understanding the impact of individual training samples without requiring repeated model retraining. However, their scalability is often limited by the…