相关论文: ESCM$^2$: Entire Space Counterfactual Multi-Task M…
Multi-scenario learning (MSL) enables a service provider to cater for users' fine-grained demands by separating services for different user sectors, e.g., by user's geographical region. Under each scenario there is a need to optimize…
A crucial design decision for any robot learning pipeline is the choice of policy representation: what type of model should be used to generate the next set of robot actions? Owing to the inherent multi-modal nature of many robotic tasks,…
As LLMs continue to scale, improving training efficiency increasingly depends on using data more effectively. Data selection addresses this problem by allocating a limited training budget to samples that best promote a target behavior.…
State-space models have been used in many applications, including econometrics, engineering, medical research, etc. The maximum likelihood estimation (MLE) of the static parameter of general state-space models is not straightforward because…
Answering counterfactual queries has important applications such as explainability, robustness, and fairness but is challenging when the causal variables are unobserved and the observations are non-linear mixtures of these latent variables,…
Recent advances in cross-prompt automated essay scoring (AES) typically train models jointly on all source prompts, often requiring additional access to unlabeled target prompt essays simultaneously. However, using all sources is suboptimal…
Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy Method (CEM), can yield compelling results even in high-dimensional control tasks and sparse-reward environments. However, their sampling inefficiency…
Bayesian inference for exponential family random graph models (ERGMs) is a doubly-intractable problem because of the intractability of both the likelihood and posterior normalizing factor. Auxiliary variable based Markov Chain Monte Carlo…
In the e-commerce advertising scenario, estimating the true probabilities (known as a calibrated estimate) on Click-Through Rate (CTR) and Conversion Rate (CVR) is critical. Previous research has introduced numerous solutions for addressing…
Conditional random field (CRF) and Structural Support Vector Machine (Structural SVM) are two state-of-the-art methods for structured prediction which captures the interdependencies among output variables. The success of these methods is…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language understanding, reasoning, and generation. However, they struggle with tasks requiring fine-grained localization and reasoning in…
Concept Bottleneck Models (CBMs) are interpretable models that predict the target variable through high-level human-understandable concepts, allowing users to intervene on mispredicted concepts to adjust the final output. While recent work…
Quantifying the data uncertainty in learning tasks is often done by learning a prediction interval or prediction set of the label given the input. Two commonly desired properties for learned prediction sets are \emph{valid coverage} and…
Conformal prediction (CP) is a wrapper around traditional machine learning models, giving coverage guarantees under the sole assumption of exchangeability; in classification problems, for a chosen significance level $\varepsilon$, CP…
Multi-task learning (MTL) has gained significant popularity in recommender systems as it enables simultaneous optimization of multiple objectives. A key challenge in MTL is negative transfer, but existing studies explored negative transfer…
Modern information retrieval systems, including web search, ads placement, and recommender systems, typically rely on learning from user feedback. Click models, which study how users interact with a ranked list of items, provide a useful…
The beam squint effect, which manifests in different steering matrices in different sub-bands, has been widely considered a challenge in millimeter wave (mmWave) multiinput multi-output (MIMO) channel estimation. Existing methods either…
In Earth System Modeling (ESM), meshes of different models usually do not match, requiring data mapping algorithms implemented in coupling software. Valcke et al. recently introduced a benchmark to evaluate such algorithms and compared…
Support vector machines (SVMs) are popular learning algorithms to deal with binary classification problems. They traditionally assume equal misclassification costs for each class; however, real-world problems may have an uneven class…
Learning is the basis of both biological and artificial systems when it comes to mimicking intelligent behaviors. From the classical PPO (Proximal Policy Optimization), there is a series of deep reinforcement learning algorithms which are…