Can a physicist make only a finite number of errors in the eternal quest to uncover the law of nature?This millennium-old philosophical problem, known as inductive inference, lies at the heart of epistemology.Despite its significance to understanding human reasoning, a rigorous justification of inductive inference has remained elusive.At a high level, inductive inference asks whether one can make at most finite errors amidst an infinite sequence of observations, when deducing the correct hypothesis from a given hypothesis class.Historically, the only theoretical guarantee has been that if the hypothesis class is countable, inductive inference is possible, as exemplified by Solomonoff induction for learning Turing machines.In this paper, we provide a tight characterization of inductive inference by establishing a novel link to online learning theory.As our main result, we prove that inductive inference is possible if and only if the hypothesis class is a countable union of online learnable classes, potentially with an uncountable size, no matter the observations are adaptively chosen or iid sampled.Moreover, the same condition is also sufficient and necessary in the agnostic setting, where any hypothesis class meeting this criterion enjoys an $\tilde{O}(\sqrt{T})$ regret bound for any time step $T$, while others require an arbitrarily slow rate of regret.Our main technical tool is a novel non-uniform online learning framework, which may be of independent interest.Our main technical tool is a novel non-uniform online learning framework, which may be of independent interest.

In many real-world decision problems there is partially observed, hidden or latent information that remains fixed throughout an interaction. Such decision problems can be modeled as Latent Markov Decision Processes (LMDPs), where a latent variable is selected at the beginning of an interaction and is not disclosed to the agent initially. In last decade, there has been significant progress in designing learning algorithms for solving LMDPs under different structural assumptions. However, for general LMDPs, there is no known learning algorithm that provably matches the existing lower bound. We effectively resolve this open question, introducing the first sample-efficient algorithm for LMDPs without . Our result builds off a new perspective on the role off-policy evaluation guarantees and coverage coefficient in LMDPs, a perspective, which has been overlooked in the context of exploration in partially observed environments. Specifically, we establish a novel off-policy evaluation lemma and introduce a new coverage coefficient for LMDPs. Then, we show how these can be used to derive near-optimal guarantees of an optimistic exploration algorithm. These results, we believe, can be valuable for a wide range of interactive learning problems beyond the LMDP class, and especially, for partially observed environments.

Shape assembly is a ubiquitous task in daily life, integral for constructing complex 3D structures like IKEA furniture. While significant progress has been made in developing autonomous agents for shape assembly, existing datasets have not yet tackled the 4D grounding of assembly instructions in videos, essential for a holistic understanding of assembly in 3D space over time. We introduce IKEA Video Manuals, a dataset that features 3D models of furniture parts, instructional manuals, assembly videos from the Internet, and most importantly, annotations of dense spatio-temporal alignments between these data modalities. To demonstrate the utility of IKEA Video Manuals, we present five applications essential for shape assembly: assembly plan generation, part-conditioned segmentation, part-conditioned pose estimation, video object segmentation, and furniture assembly based on instructional video manuals. For each application, we provide evaluation metrics and baseline methods. Through experiments on our annotated data, we highlight many challenges in grounding assembly instructions in videos to improve shape assembly, including handling occlusions, varying viewpoints, and extended assembly sequences.

Due to the recent remarkable advances in artificial intelligence, researchers have begun to consider challenging learning problems such as learning to generalize behavior from large offline datasets or learning online in non-Markovian environments. Meanwhile, recent advances in both of these areas have increasingly relied on conditioning policies on large context lengths. A natural question is if there is a limit to the performance benefits of increasing the context length if the computation needed is available. In this work, we establish a novel theoretical result that links the context length of a policy to the time needed to reliably evaluate its performance (i.e., its mixing time) in large scale partially observable reinforcement learning environments that exhibit latent sub-task structure. This analysis underscores a key tradeoff: when we extend the context length, our policy can more effectively model non-Markovian dependencies, but this comes at the cost of potentially slower policy evaluation and as a result slower downstream learning. Moreover, our empirical results highlight the relevance of this analysis when leveraging Transformer based neural networks. This perspective will become increasingly pertinent as the field scales towards larger and more realistic environments, opening up a number of potential future directions for improving the way we design learning agents.

Existing benchmarks for evaluating LLMs' cultural sensitivities are usually limited to a single language or online sources like Wikipedia, which may not reflect the daily habits, customs, and lifestyles of different regions. That is, information about the food people eat for their birthday celebrations, spices they typically use, musical instruments youngsters play or the sports they practice in school is not always explicitly written online. To address this issue, we introduce BLEnD, a hand-crafted benchmark designed to evaluate LLMs' everyday knowledge across diverse cultures and languages. The benchmark comprises 52.6k question-answer pairs from 16 countries/regions, in 13 different languages, including low-resource ones such as Amharic, Assamese, Azerbaijani, Hausa, and Sundanese. We evaluate LLMs in two formats: short-answer questions, and multiple-choice questions. We show that LLMs perform better in cultures that are more present online, with a maximum 57.34% difference in GPT-4, the best-performing model, in the short-answer format.Furthermore, we find that LLMs perform better in their local languages for mid-to-high-resource languages. Interestingly, for languages deemed to be low-resource, LLMs provide better answers in English. We make our dataset publicly available at: https://github.com/nlee0212/BLEnD.

How (dis)similar are the learning trajectories of vision-language models and children? Recent modeling work has attempted to understand the gap between models' and humans' data efficiency by constructing models trained on less data, especially multimodal naturalistic data. However, such models are often evaluated on adult-level benchmarks, with limited breadth in language abilities tested, and without direct comparison to behavioral data. We introduce DevBench, a multimodal benchmark comprising seven language evaluation tasks spanning the domains of lexical, syntactic, and semantic ability, with behavioral data from both children and adults. We evaluate a set of vision-language models on these tasks, comparing models and humans on their response patterns, not their absolute performance. Across tasks, models exhibit variation in their closeness to human response patterns, and models that perform better on a task also more closely resemble human behavioral responses. We also examine the developmental trajectory of OpenCLIP over training, finding that greater training results in closer approximations to adult response patterns. DevBench thus provides a benchmark for comparing models to human language development. These comparisons highlight ways in which model and human language learning processes diverge, providing insight into entry points for improving language models.

How the data center boom plunged one small Pennsylvania town into chaos. Valley View Estates is set to be surrounded by data centers. Get your news from a source that's not owned and controlled by oligarchs. "I don't like to see anyone upset," said Nick Farris of Provident Real Estate Advisors. He was sitting in the front of a crowd of roughly 150 inside Valley View High School's auditorium in Archbald, a town of about 7,500, huddled between two mountain ranges in Pennsylvania's Lackawanna Valley. Farris was there to represent the developer for Project Scott, one of many data center campuses coming to town. "I think that this is the best data center site in this area of the country, by far." The audience had been fairly quiet, bundled in thick coats against the late January cold. But as Farris spoke about data centers as a boon for communities, they began to laugh, drawing a rebuke from town officials. "What about the children?" someone shouted from the crowd. The children were watching from the walls; long banners of Valley View Performing Arts students hanging around the auditorium like championship pennants. Project Scott and four other data facilities will sit just a few thousand feet from the middle and high schools. He was referring to Lockheed Martin's 350,000-square-foot Missiles and Fire Control facility directly next to the high school, parts of which are highly contaminated . "That sucks too!" another attendee yelled back.

Models for student reading performance can empower educators and institutions to proactively identify at-risk students, thereby enabling early and tailored instructional interventions. However, there are no suitable publicly available educational datasets for modeling and predicting future reading performance. In this work, we introduce the Enhanced Core Reading Instruction (ECRI) dataset, a novel large-scale longitudinal tabular dataset collected across 44 schools with 6,916 students and 172 teachers. We leverage the dataset to empirically evaluate the ability of state-of-the-art machine learning models to recognize early childhood educational patterns in multivariate and partial measurements. Specifically, we demonstrate a simple self-supervised strategy in which a Multi-Layer Perception (MLP) network is pre-trained over masked inputs to outperform several strong baselines while generalizing over diverse educational settings. To facilitate future developments in precise modeling and responsible use of models for individualized and early intervention strategies, our data and code are available at https://ecri-data.github.io/.

Increased training parameters have enabled large pre-trained models to excel in various downstream tasks. Nevertheless, the extensive computational requirements associated with these models hinder their widespread adoption within the community. We focus on Knowledge Distillation (KD), where a compact student model is trained to mimic a larger teacher model, facilitating the transfer of knowledge of large models. In contrast to much of the previous work, we scale up the parameters of the student model during training, to benefit from over-parameterization without increasing the inference latency. In particular, we propose a tensor decomposition strategy that effectively over-parameterizes the relatively small student model through an efficient and nearly lossless decomposition of its parameter matrices into higher-dimensional tensors. To ensure efficiency, we further introduce a tensor constraint loss to align the high-dimensional tensors between the student and teacher models.

Graphical User Interface (GUI) automation holds significant promise for enhancing human productivity by assisting with computer tasks. Existing task formulations primarily focus on simple tasks that can be specified by a single, language-only instruction, such as "Insert a new slide." In this work, we introduce VideoGUI, a novel multi-modal benchmark designed to evaluate GUI assistants on visual-centric GUI tasks. Sourced from high-quality web instructional videos, our benchmark focuses on tasks involving professional and novel software (e.g., Adobe Pho-toshop or Stable Diffusion WebUI) and complex activities (e.g., video editing). VideoGUI evaluates GUI assistants through a hierarchical process, allowing for identification of the specific levels at which they may fail: (i) high-level planning: reconstruct procedural subtasks from visual conditions without language descriptions; (ii) middle-level planning: generate sequences of precise action narrations based on visual state (i.e., screenshot) and goals; (iii) atomic action execution: perform specific actions such as accurately clicking designated elements. For each level, we design evaluation metrics across individual dimensions to provide clear signals, such as individual performance in clicking, dragging, typing, and scrolling for atomic action execution. Our evaluation on VideoGUI reveals that even the SoTA large multimodal model GPT4o performs poorly on visual-centric GUI tasks, especially for high-level planning.