Related papers: Bicoptor 2.0: Addressing Challenges in Probabilist…

Matching job descriptions (JDs) with suitable talent requires models capable of understanding not only textual similarities between JDs and candidate resumes but also contextual factors such as geographical location and academic seniority.…

Click-through rate (CTR) prediction is a core task in recommender systems. Existing methods (IDRec for short) rely on unique identities to represent distinct users and items that have prevailed for decades. On one hand, IDRec often faces…

As language models increase in size by the day, methods for efficient inference are critical to leveraging their capabilities for various applications. Prior work has investigated techniques like model pruning, knowledge distillation, and…

Secure comparison and secure selection are two fundamental MPC (secure Multi-Party Computation) protocols. One important application of these protocols is the secure ReLU and DReLU computation in privacy preserving deep learning. In this…

Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF), designed to improve training simplicity and stability by redefining reward functions.…

Machine learning (ML) involves private data and proprietary model parameters. MPC-based ML allows multiple parties to collaboratively run an ML workload without sharing their private data or model parameters using multi-party computing…

Leveraging machine learning (ML) to predict an initial solution for mixed-integer linear programming (MILP) has gained considerable popularity in recent years. These methods predict a solution and fix a subset of variables to reduce the…

We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's confidence, without requiring any auxiliary models or…

In multi-party collaborative learning, the parameter server sends a global model to each data holder for local training and then aggregates committed models globally to achieve privacy protection. However, both the dragger issue of…

Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However, HRL methods face two fundamental challenges: (i) non-stationarity caused by the evolving…

This paper introduces PriMaL, a general PRIvacy-preserving MAchine-Learning method for reducing the privacy cost of information transmitted through a network. Distributed sensor networks are often used for automated classification and…

Fine-tuning pretrained large models to downstream tasks is an important problem, which however suffers from huge memory overhead due to large-scale parameters. This work strives to reduce memory overhead in fine-tuning from perspectives of…

Deduplication is a vital preprocessing step that enhances machine learning model performance and saves training time and energy. However, enhancing federated learning through deduplication poses challenges, especially regarding scalability…

Storing open-source fine-tuned models separately introduces redundancy and increases response times in applications utilizing multiple models. Delta-parameter pruning (DPP), particularly the random drop and rescale (DARE) method proposed by…

In this paper, we present a distributed algorithm for solving convex, constraint-coupled, optimization problems over peer-to-peer networks. We consider a network of processors that aim to cooperatively minimize the sum of local cost…

Reinforcement learning is widely used in applications where one needs to perform sequential decisions while interacting with the environment. The problem becomes more challenging when the decision requirement includes satisfying some safety…

Quality pretraining data is often seen as the key to high-performance language models. However, progress in understanding pretraining data has been slow due to the costly pretraining runs required for data selection experiments. We present…

Differential privacy (DP) has established itself as one of the standards for ensuring privacy of individual data. However, reasoning about DP is a challenging and error-prone task, hence methods for formal verification and refutation of DP…

We introduce stochastic activations. This novel strategy randomly selects between several non-linear functions in the feed-forward layer of a large language model. In particular, we choose between SILU or RELU depending on a Bernoulli draw.…

Large language models (LLMs) exhibit exceptional performance across a wide range of tasks; however, their token-by-token autoregressive generation process significantly hinders inference speed. Speculative decoding presents a promising…