Deep learning classifiers are assisting humans in making decisions and hence the user's trust in these models is of paramount importance. Trust is often a function of constant behavior. From an AI model perspective it means given the same input the user would expect the same output, especially for correct outputs, or in other words consistently correct outputs. This paper studies a model behavior in the context of periodic retraining of deployed models where the outputs from successive generations of the models might not agree on the correct labels assigned to the same input. We formally define consistency and correct-consistency of a learning model. We prove that consistency and correct-consistency of an ensemble learner is not less than the average consistency and correct-consistency of individual learners and correct-consistency can be improved with a probability by combining learners with accuracy not less than the average accuracy of ensemble component learners. To validate the theory using three datasets and two state-ofthe-art deep learning classifiers we also propose an efficient dynamic snapshot ensemble method and demonstrate its value.

The guidance scale of the diffusion model is set as 2.0, and the sampling step is 50. For synthetic pre-training, we adopt exactly the same training protocols as real images. Then, during fine-tuning, the base learning rate is decayed to be half of the normal learning rate. Since our whole model parameters are pre-trained with synthetic images, the fine-tuning learning rate is the same throughout the whole model. The model is pre-trained and fine-tuned for the same iterations as real images.

In the fixed budget thresholding bandit problem, an algorithm sequentially allocates a budgeted number of samples to different distributions. It then predicts whether the mean of each distribution is larger or lower than a given threshold. We introduce a large family of algorithms (containing most existing relevant ones), inspired by the Frank-Wolfe algorithm, and provide a thorough yet generic analysis of their performance. This allowed us to construct new explicit algorithms, for a broad class of problems, whose losses are within a small constant factor of the non-adaptive oracle ones. Quite interestingly, we observed that adaptive methods empirically greatly out-perform non-adaptive oracles, an uncommon behavior in standard online learning settings, such as regret minimization. We explain this surprising phenomenon on an insightful toy problem.

Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning.

We give a model of how to infer natural language rules by doing experiments.

Large language models (LLMs) have achieved unprecedented performances in various applications, yet evaluating them is still challenging. Existing benchmarks are either manually constructed or are automatic, but lack the ability to evaluate the thought process of LLMs with arbitrary complexity. We contend that utilizing existing relational databases based on the entity-relationship (ER) model is a promising approach for constructing benchmarks as they contain structured knowledge that can be used to question LLMs. Unlike knowledge graphs, which are also used to evaluate LLMs, relational databases have integrity constraints that can be used to better construct complex in-depth questions and verify answers: (1) functional dependencies can be used to pinpoint critical keywords that an LLM must know to properly answer a given question containing certain attribute values; and (2) foreign key constraints can be used to join relations and construct multi-hop questions, which can be arbitrarily long and used to debug intermediate answers. We thus propose ERBench, which uses these integrity constraints to convert any database into an LLM benchmark. ERBench supports continuous evaluation as databases change, multimodal questions, and various prompt engineering techniques. In our experiments, we construct LLM benchmarks using databases of multiple domains and make an extensive comparison of contemporary LLMs. We show how ER-Bench can properly evaluate any LLM by not only checking for answer correctness, but also effectively verifying the rationales by looking for the right keywords.