Method learns latent states from rich observations to improve RL exploration.
problem Improving RL performance with rich observations and latent states.
method Estimates latent states from observations through regression and clustering, providing finite-sample guarantees.
result Exponential improvement over Q-learning with naïve exploration. Efficiently extracts linear dynamics from complex observations.
problem Learning policies directly from rich, high-dimensional observations.
method Modeling linear dynamics in a hidden subspace and developing an efficient algorithm.
result Successfully extracts linear dynamics from rich observations.
We study the computational tractability of PAC reinforcement learning with rich observations. We present new provably sample-efficient algorithms for environments with deterministic hidden state dynamics and stochastic rich observations. These methods operate in an oracle model of computation -- accessing policy and va…
New metric measures dynamical richness without relying on accuracy.
problem Lack of a reliable metric for measuring dynamical richness.
method Developed a computationally efficient, performance-independent metric based on low-rank bias.
result Metric recovers neural collapse as a special case and captures known transitions without accuracy.
RDPD uses KD to improve models trained on poor data using rich data from other environments.
problem Deploying models in environments with varying data quality and quantity.
method Knowledge distillation from high-quality, rich data to improve low-quality, poor data models.
result RDPD models consistently outperform baselines and state-of-the-art methods across multiple datasets.
HOMER learns latent states to explore rich environments efficiently.
problem Exploration in rich observation environments with unknown latent states.
method Interleaves representation learning and strategic exploration to identify kinematic states.
result Provably efficient exploration with polynomial sample complexity in latent states and time horizon.
Study shows how initialization scale controls transition between kernel and rich regimes in overparametrized models.
problem Understanding the transition between kernel and rich regimes in overparametrized models.
method Analysis of simple two-layer model and complex matrix factorization models, demonstrating the transition.
result Scale of initialization controls the transition between kernel and rich regimes, affecting generalization properties.
We propose and study a new model for reinforcement learning with rich observations, generalizing contextual bandits to sequential decision making. These models require an agent to take actions based on observations (features) with the goal of achieving long-term performance competitive with a large set of policies. To …
The rich-get-richer mechanism (agents increase their ``wealth'' randomly at a rate proportional to their holdings) is often invoked to explain the Pareto power-law distribution observed in many physical situations, such as the degree distribution of growing scale free nets. We use two different analytical approaches, a…
The paper proposes an algorithm to learn causal state representations for partially observable environments.
problem Learning task-agnostic state abstractions in partially observable environments.
method The approach involves learning approximate causal state representations from RNNs trained to predict observations given the history.
result The learned state representations are useful for efficient policy learning in reinforcement learning problems with rich observation spaces.
Reinforcement learning (RL) in Markov decision processes (MDPs) with large state spaces is a challenging problem. The performance of standard RL algorithms degrades drastically with the dimensionality of state space. However, in practice, these large MDPs typically incorporate a latent or hidden low-dimensional structu…
Study on how initialization scale affects neural network training regimes.
problem Understanding the transition between kernel and rich regimes in overparametrized models.
method Analysis of simple depth-D models and empirical testing on complex models.
result Scale of initialization controls transition between kernel and rich regimes.
Motivated by the widespread adoption of large-scale A/B testing in industry, we propose a new experimentation framework for the setting where potential experiments are abundant (i.e., many hypotheses are available to test), and observations are costly; we refer to this as the experiment-rich regime. Such scenarios requ…
Paper tackles reinforcement learning with complex observations and simple latent dynamics.
problem Understanding reinforcement learning with complex observations and simple latent dynamics.
method Statistical and algorithmic analysis of reinforcement learning under general latent dynamics.
result Identifies latent pushforward coverability as a condition for statistical tractability.
Study on rich regime training in deep learning, finding active parameters in bottom layers.
problem Understanding the practical success of deep learning models.
method Empirical study on rich regime training with benchmark datasets, re-initialization analysis, and probabilistic Layer-Wise Sparse SGD.
result Probabilistic Layer-Wise Sparse SGD matches vanilla SGD's generalization performance with improved efficiency.
New method uses adversarial training for structural model estimation.
problem Estimating structural models with high accuracy.
method Adversarial training between generator and discriminator.
result Adversarial estimator achieves parametric efficiency under correct specification.
OMLE combines optimism and MLE for efficient sequential decision making.
problem Efficiently solving sequential decision making problems, especially in partially observable settings.
method Combines optimism for exploration and maximum likelihood estimation for model learning.
result OMLE learns near-optimal policies for a wide range of sequential decision making problems.
We provide an exact solution to the ideal-gas-like models studied in econophysics to understand the microscopic origin of Pareto-law. In these class of models the key ingredient necessary for having a self-organized scale-free steady-state distribution is the trading or collision rule where agents or particles save a d…
In many settings, we have multiple data sets (also called views) that capture different and overlapping aspects of the same phenomenon. We are often interested in finding patterns that are unique to one or to a subset of the views. For example, we might have one set of molecular observations and one set of physiologica…
Semi-supervised learning benefits the rich more than the poor, affecting fairness.
problem Disparate impact of semi-supervised learning on different sub-populations.
method Theoretical and empirical analysis of a broad family of SSL algorithms using pseudo-labels.
result Semi-supervised learning benefits the rich more than the poor, potentially violating fairness.
SentenceMIM learns rich latent representations for variable-length language data.
problem Challenges in learning VAEs for variable-length language data, especially posterior collapse.
method Probabilistic auto-encoder trained with Mutual Information Machine (MIM) learning.
result SentenceMIM learns informative latent representations with high mutual information.
Clusters cryptocurrency market states via cross correlation analysis.
problem Analyse cryptocurrency market dynamics.
method Cross correlation structure analysis over 5 years.
result Cryptocurrency market clusters into 4 states.
A new curiosity method uses episodic memory to reward novelty, improving learning from sparse rewards.
problem Sparse rewards in real-world reinforcement learning.
method Uses episodic memory to form novelty bonuses based on reachability.
result Improves learning from sparse rewards in various environments.
Study shows large extra dimensions are hidden from view by black holes.
problem Difficulty in observing large extra dimensions in the universe.
method Analysis of conditions leading to black hole formation in lower dimensional theories.
result Extra dimensions larger than 10−19m are hidden inside black holes. ML methods improve planetary science data analysis.
problem Insufficient use of ML in planetary science.
method Ten recommendations for integrating ML in planetary science.
result Expanding planetary science insights from large datasets.
Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy. Recently, high-dimensional parametric models like neural networks have succeeded in building rich representations using either compressive, reconstructive or supervised criteria. However, the seman…
IDS optimizes regret in stochastic partial monitoring with linear rewards.
problem Optimizing decision-making in uncertain environments with linear rewards.
method Information Directed Sampling (IDS) for stochastic partial monitoring.
result Achieves optimal regret rates in all observable game regimes.
Transformers capture combinatorial tasks with bounded error and logarithmic sample dependence.
problem Capturing complex combinatorial tasks with bounded error and sample efficiency.
method Formal definition of algorithmic capture, empirical analysis of infinite-width transformers, upper bounds on computational complexity.
result Transformers exhibit an inductive bias favoring simpler algorithmic procedures over higher complexity ones.
The paper develops a method to create robust control policies for robots using information bottlenecks.
problem Robotic control policies are sensitive to task-irrelevant state and sensor changes.
method Derives a policy gradient algorithm that creates an information bottleneck between states and task-relevant representations.
result Task-driven policies are more robust to sensor noise and environmental changes.
In the scenario of real-time monitoring of hospital patients, high-quality inference of patients' health status using all information available from clinical covariates and lab tests is essential to enable successful medical interventions and improve patient outcomes. Developing a computational framework that can learn…
BYOL-Explore learns to explore visually-rich environments by predicting world dynamics.
problem Exploration in visually complex environments.
method Optimizes a single prediction loss in latent space to learn world representation, dynamics, and exploration policy.
result Achieves superhuman performance on Atari games with simpler design.
Tools of the theory of critical phenomena, namely the scaling analysis and universality, are argued to be applicable to large complex web-like network structures. Using a detailed analysis of the real data of the International Trade Network we argue that the scaled link weight distribution has an approximate log-normal…
RichID learns optimal control policies from nonlinear observations.
problem Continuous control with unknown nonlinearity in system model.
method RichID algorithm using a least-squares regression oracle.
result First provable sample complexity guarantee for continuous control.
When learning a hidden Markov model (HMM), sequen- tial observations can often be complemented by real-valued summary response variables generated from the path of hid- den states. Such settings arise in numerous domains, includ- ing many applications in biology, like motif discovery and genome annotation. In this pape…
CHEER boosts poor models using rich model knowledge.
problem Improving performance of models trained on limited data.
method Develops CHEER framework to infuse rich model knowledge into poor models.
result CHEER significantly improves model performance on physiological datasets.
Consider a Riemannian metric on two-torus. We prove that the question of existence of polynomial first integrals leads naturally to a remarkable system of quasi-linear equations which turns out to be a Rich system of conservation laws. This reduces the question of integrability to the question of existence of smooth (q…
Study explores properties of bipartite knots.
problem None explicitly stated; focuses on properties of bipartite knots.
method Exploration of combinatorial structure.
result Rich combinatorial structure of bipartite knots.
The paper explains the richness scale of wide neural networks.
problem Understanding the behavior of overparameterized neural networks.
method Nonrigorous derivation and empirical evidence.
result Wide neural networks exhibit a richness scale from lazy kernel behavior to feature learning.
SHMM models human mobility from GPS and text data, overcoming text sparsity.
problem Modeling human mobility from semantic trace data, especially addressing text sparsity.
method SHMM is a multi-modal spherical hidden Markov model that jointly models location, time, and text embeddings on a unit sphere using vMF distribution.
result SHMM outperforms state-of-the-art models in next location prediction and has lower training cost.
The electronic health record (EHR) provides an unprecedented opportunity to build actionable tools to support physicians at the point of care. In this paper, we investigate survival analysis in the context of EHR data. We introduce deep survival analysis, a hierarchical generative approach to survival analysis. It depa…
This paper tackles sample-efficient reinforcement learning for partially observable Markov games.
problem Learning in partially observable Markov games with incomplete information.
method A simple algorithm combining optimism and Maximum Likelihood Estimation (MLE) for self-play, and a variant of optimistic MLE for adversarial opponents.
result The proposed algorithms achieve approximate Nash, correlated, and coarse correlated equilibria in polynomial samples for weakly revealing POMGs.
This paper studies systematic exploration for reinforcement learning with rich observations and function approximation. We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our first contribution is a complexity measure, the Bellman rank, that we show enables …
RICH models scenes as hierarchical tree to learn and generate complex compositions.
problem Learning compositional structures between parts and objects in natural scenes.
method RICH uses a latent scene graph to organize entities into a tree structure and employs a top-down inference approach.
result RICH learns and generates complex scene hierarchies from unlabeled data.
Study binary choice with asymmetric loss, offering simple solutions.
problem Binary choice with asymmetric loss in data-rich environments.
method Loss-based reweighting of logistic regression or machine learning techniques.
result Valid decisions on binary outcomes with general loss functions.
This paper proposes new get-rich-quick schemes that involve trading in a financial security with a non-degenerate price path. For simplicity the interest rate is assumed zero. If the price path is assumed continuous, the trader can become infinitely rich immediately after it becomes non-constant (if it ever does). If i…
An Artificial Intelligence (AI) system is an autonomous system which emulates human mental and physical activities such as Observe, Orient, Decide, and Act, called the OODA process. An AI system performing the OODA process requires a semantically rich representation to handle a complex real world situation and ability …
Kernel ridge regression for causal inference with missing data.
problem Estimating treatment effects with missing data in selected samples.
method Kernel ridge regression estimators for nonparametric dose response curves and semiparametric treatment effects.
result Uniform consistency and finite sample rates for continuous treatment, root-n consistency for discrete treatment.
Bayesian analysis predicts properties of proton-emitting nuclei beyond the proton drip line.
problem Predicting properties of unstable nuclei in the proton-rich region.
method Bayesian Gaussian processes and mass models corrected with statistical emulators.
result Quantified predictions for separation energies and probabilities of proton emission.