arXiv research

A new method for ILO with transition model disparity using an intermediary policy.

Diffusion maps help learn complex quantum phase transitions from data.

Quantum theory reinterprets financial pricing by focusing on observable price transitions.

Study on estimating sparse transition matrix of partially-observed VAR with noisy and sparse data.

A new algorithm uses IVs to learn optimal policies from observational data.

We find numerical and empirical evidence for dynamical, structural and topological phase transitions on the (German) Frankfurt Stock Exchange (FSE) in the temporal vicinity of the worldwide financial crash. Using the Minimal Spanning Tree (MST) technique, a particularly useful canonical tool of the graph theory, two tr…

New STH distance finds patterns in event timeseries without resampling.

New algorithms handle phase retrieval with rank d measurements, revealing phase transitions.

We argue that in fully-connected networks a phase transition delimits the over- and under-parametrized regimes where fitting can or cannot be achieved. Under some general conditions, we show that this transition is sharp for the hinge loss. In the whole over-parametrized regime, poor minima of the loss are not encounte…

Expands Hidden Markov Model to include Markov chain observations.

New method identifies latent causal variables from observed data, overcoming indeterminacies.

Descending phase retrieval algorithms show a phase transition with increasing sample complexity.

A Longitudinal Attribute-Conditioned Neural Network (LANTERN) framework for modeling health-state transition probabilities in irregular longitudinal data.

Study models forest transitions with deep learning for parameter estimation.

New method identifies common cause in causal insufficiency, revealing complex phase transitions.

In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system …

This paper presents a general theory that aims at explaining timescales observed empirically in technology transitions and predicting those of future transitions. This framework is used further to derive a theory for exploring the dynamics that underlie the complex phenomenon of irreversible and path dependent price or…

Study shows Elo models fail to accurately measure transitive strength in competitive games.

Modeling financial markets as gas molecules, the paper predicts phase transitions similar to water and steam.

We search for digital biomarkers from Parkinson's Disease by observing approximate repetitive patterns matching hypothesized step and stride periodic cycles. These observations were modeled as a cycle of hidden states with randomness allowing deviation from a canonical pattern of transitions and emissions, under the hy…

The paper develops ML algorithms for calibrating credit rating transition models for high and low default portfolios.

New method learns diffusion transition density for Bayesian inference.

Bayesian theory explains abrupt emergence of copy subcircuit in attention.

We fill a void in merging empirical and phenomenological characterisation of the dynamical phase transitions in complex systems by identifying three of them on real-life financial markets. We extract and interpret the empirical, numerical, and semi-analytical evidences for the existence of these phase transitions, by c…

New framework learns policies for partially observable systems.

Develops a new framework for conditional independence.

Study of surface defects in gauge theories leads to duality and separation of variables.

In this paper, we study the sensitivity of the spectral clustering based community detection algorithm subject to a Erdos-Renyi type random noise model. We prove phase transitions in community detectability as a function of the external edge connection probability and the noisy edge presence probability under a general…

Study shows optimal RL with transition look-ahead is NP-hard for $\ell \geq 2$.

Algorithm learns graph operator from sparse space-time samples.

We generalize the observable diameter and the separation distance for metric measure spaces to those for pyramids, and prove some limit formulas for these invariants for a convergent sequence of pyramids. We obtain various applications of our limit formulas as follows. We have a criterion of the phase transition proper…

Identifies latent actions and dynamics from offline data with diverse demonstrators.

Algorithm improves RL by discovering delayed causal relations.

Several methods exist to infer causal networks from massive volumes of observational data. However, almost all existing methods require a considerable length of time series data to capture cause and effect relationships. In contrast, memory-less transition networks or Markov Chain data, which refers to one-step transit…

Reward hacking exploits misspecified rewards, affecting agent capabilities and true performance.

New method for state inference in state-space models with unknown dynamics.

Study finds phase transition in context-sensitive language model with short-range interactions.

Percolation on complex networks has been used to study computer viruses, epidemics, and other casual processes. Here, we present conditions for the existence of a network specific, observation dependent, phase transition in the updated posterior of node states resulting from actively monitoring the network. Since tradi…

Study learns linear system dynamics from noisy bilinear data.

Modeling dynamical systems is important in many disciplines, e.g., control, robotics, or neurotechnology. Commonly the state of these systems is not directly observed, but only available through noisy and potentially high-dimensional observations. In these cases, system identification, i.e., finding the measurement map…

CtrlNS learns latent factors and distribution shifts from sparse transitions without prior knowledge.

Improved POMDP regret to sqrt(T) with known observation model.

Optimal strategy for reinforcement learning with delayed observations.

High-dimensional time series data exist in numerous areas such as finance, genomics, healthcare, and neuroscience. An unavoidable aspect of all such datasets is missing data, and dealing with this issue has been an important focus in statistics, control, and machine learning. In this work, we consider a high-dimensiona…

Neural models learn continuous-time Markov chain transition rates from data.

Linear recurrent networks explain reinforcement learning performance in partially observable settings.

New filters for non-linear systems achieve closed-form solutions.

In the Information Bottleneck (IB), when tuning the relative strength between compression and prediction terms, how do the two terms behave, and what's their relationship with the dataset and the learned representation? In this paper, we set out to answer these questions by studying multiple phase transitions in the IB…