9 accepted papers
Aligning large language models (LLMs) to diverse human preferences is fundamentally challenging since criteria can often conflict with each other. Inference-time alignment methods have recently gained popularity as they allow LLMs to be aligned to multiple criteria via different alignment algorithms…
A longstanding goal in safe reinforcement learning (RL) is a method to ensure the safety of a policy throughout the entire process, from learning to operation. However, existing safe RL paradigms inherently struggle to achieve this objective. We propose a method, called Provably Lifetime Safe RL (PL…
We propose a method of offline reinforcement learning (RL) featuring the performance guarantee without any assumptions on the data support. Under such conditions, estimating or optimizing the conventional performance metric is generally infeasible due to the distributional discrepancy between data a…
We are interested in an evaluation methodology for molecular optimization. Given a sample of molecules and their properties of our interest, we wish not only to train a generator of molecules optimized with respect to a target property but also to evaluate its performance accurately. A common practi…
We address the problem of predicting when a disease will develop, i.e., medical event time (MET), from a patient's electronic health record (EHR). The MET of non-communicable diseases like diabetes is highly correlated to cumulative health conditions, more specifically, how much time the patient sp…
Partially monotone regression is a regression analysis in which the target values are monotonically increasing with respect to a subset of input features. The TensorFlow Lattice library is one of the standard machine learning libraries for partially monotone regression. It consists of several neu…
We are concerned with the problem of distributional prediction with incomplete features: The goal is to estimate the distribution of target variables given feature vectors with some of the elements missing. A typical approach to this problem is to perform missing-value imputation and regression, sim…
We consider the problem of offline policy evaluation~(OPE) with Markov decision processes~(MDPs), where the goal is to estimate the utility of given decision-making policies based on static datasets. Recently, theoretical understanding of OPE has been rapidly advanced under (approximate) realizabili…
We develop a new theoretical framework, the envelope complexity, to analyze the minimax regret with logarithmic loss functions. Within the framework, we derive a Bayesian predictor that adaptively achieves the minimax regret over high-dimensional l1-balls within a factor of two. The prior is newly d…