Cloned HMMs efficiently learn variable order sequences without local minima issues.
problem Learning long-term temporal structure in sequences.
method Constrained HMMs with a sparsity structure that maps hidden states deterministically to emissions.
result Cloned HMMs can model temporal dependencies at arbitrarily long distances and recognize contexts with 'holes'.
GMM-HMMs improve malware classification compared to discrete HMMs.
problem Improving malware classification accuracy using GMM-HMM models.
method Used GMM-HMM models for opcode and entropy-based features comparison with discrete HMMs.
result GMM-HMMs generally improve significantly on entropy-based features classification results.
Develops a more flexible HDP-HMM for temporal data segmentation.
problem Limited expressiveness of sticky HDP-HMM due to stationary self-persistence probability.
method Introduces recurrent sticky HDP-HMM with a novel Gibbs sampling strategy.
result RS-HDP-HMM outperforms other models in segmentation tasks.
Paper proposes Cycle-of-Learning framework for better reinforcement learning performance.
problem Efficiently updating policies trained with demonstrations using reinforcement learning.
method Cycle-of-Learning framework combining behavior cloning and 1-step Q-learning losses.
result Cycle-of-Learning framework improves reinforcement learning performance in dense and sparse reward scenarios.
Paper presents a machine learning method to predict cancer sub-clones.
problem Predicting the growth of sub-clones in cancer tumors.
method Data-driven machine learning approach to capture sub-clonal characteristics.
result Machine learning can predict which sub-clones are more likely to grow.
A new model separates persistence and transition priors in HDP-HMM.
problem Limitation of sticky HDP-HMM in expressing different persistence strengths.
method Developed a disentangled sticky HDP-HMM (DS-HDP-HMM) with novel Gibbs sampling algorithms.
result DS-HDP-HMM outperforms sticky HDP-HMM and HDP-HMM on synthetic and real data.
Paper introduces DNTs to clone black-box models efficiently.
problem Cloning functionality of black-box models.
method Deep Neural Trees (DNTs) trained with active learning.
result Trained DNT can clone task-specific behavior of black-box models.
This paper provides theoretical foundations for using quantized actions in behavior cloning.
problem Applying autoregressive models to continuous control requires discretizing actions through quantization, which is poorly understood.
method The paper analyzes quantization error propagation and statistical sample complexity, and proposes model-based augmentation.
result Behavior cloning with quantized actions achieves optimal sample complexity, matching existing lower bounds.
The paper provides theoretical guarantees for behavior cloning using generative models.
problem Behavior cloning of complex expert demonstrations using generative models.
method The paper proposes a theoretical framework invoking low-level controllers to stabilize imitation around expert demonstrations. It shows that with suitable low-level stability guarantees and powerful generative models, pure supervised behavior cloning can match expert trajectories.
result The paper proves that with a suitable low-level stability guarantee and a powerful enough generative model, pure supervised behavior cloning can generate trajectories matching the per-time step distribution of essentially arbitrary expert trajectories in an optimal transport cost.
As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks (RNNs), state of the art models in speech re…
Behavior cloning training instabilities amplified by SGD noise over long horizons.
problem Training instabilities in behavior cloning with deep neural networks.
method Empirical dissection of minibatch SGD updates and their effects on long-horizon rewards.
result Exponential moving average (EMA) of iterates effectively mitigates gradient variance amplification (GVA).
Hybridizes LSTM and HMM for improved language model performance.
problem Improving the performance of LSTM and HMM models.
method Analyzes hidden state structures, compares predictive accuracy and hidden state output of LSTM and HMM.
result HMM can serve as an appropriate approximation of LSTM model.
The susceptibility of deep learning to adversarial attack can be understood in the framework of the Renormalisation Group (RG) and the vulnerability of a specific network may be diagnosed provided the weights in each layer are known. An adversary with access to the inputs and outputs could train a second network to clo…
HMRNN combines HMMs and neural networks for Alzheimer's disease forecasting.
problem Improving disease progression modeling with hidden states not fully known.
method Developed HMRNN combining HMMs and recurrent neural networks.
result HMRNN improves disease forecasting and offers novel clinical interpretation.
New method minimizes f-divergence for better imitation learning.
problem Learning from multi-modal demonstrations, especially interpolating between modes.
method Minimizing reverse KL divergence or I-projection for any f-divergence.
result Our method reliably imitates multi-modal behaviors better than existing methods.
We study the problem of learning overcomplete HMMs---those that have many hidden states but a small output alphabet. Despite having significant practical importance, such HMMs are poorly understood with no known positive or negative results for efficient learning. In this paper, we present several new results---both po…
The paper uses HMM and LSTM for stock market trend analysis.
problem Predicting stock market trends using machine learning.
method Apply Hidden Markov Model and Long Short Term Memory to stock market data.
result The combination of GMM-HMM+LSTM and XGB-HMM+LSTM outperformed other models.
LC-CRFs are equivalent to HMMs, and MPM/MAP classifiers can be reformulated as CRFs.
problem Comparing and reformulating HMMs and CRFs.
method Demonstrating equivalence and reformulation of classifiers.
result LC-CRFs are equivalent to HMMs, and MPM/MAP classifiers can be reformulated as CRFs.
The paper analyzes the value discrepancies of imitation learning methods.
problem Analyzing the value discrepancies of imitation learning methods.
method Discrepancy propagation analysis for infinite-horizon settings.
result GAIL has less compounding errors than behavioral cloning.
The hidden Markov model (HMM) is a generative model that treats sequential data under the assumption that each observation is conditioned on the state of a discrete hidden variable that evolves in time as a Markov chain. In this paper, we derive a novel algorithm to cluster HMMs through their probability distributions.…
MAZE attacks a model without data, using synthetic inputs.
problem Model Stealing attacks that require data to replicate a target model.
method MAZE uses zeroth-order gradient estimation to create synthetic inputs.
result MAZE achieves high clone accuracy without data.
New method estimates HMM hidden states efficiently.
problem Inaccurate posterior predictive distribution in HMMs.
method Autoregressive-flow for estimating hidden states.
result Estimates comparable to SMC algorithm.
Paper tackles HMM learning with unknown missing observation locations.
problem Learning HMMs with missing data locations unknown.
method Proposes reconstruction algorithms without structural assumptions.
result Can reconstruct process dynamics as if missing locations were known.
Paper tackles efficient HMM learning with conditional samples.
problem Cryptographic hardness in learning HMMs from i.i.d. samples.
method Interactive access model, polynomial-time algorithms for conditional probabilities and latent low rank structures.
result Efficient algorithms for HMM learning in both exact and approximate conditional settings.
As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks, state of the art models in speech recogniti…
New technique improves imitation learning by preventing local minima and exploring states.
problem Behavioral cloning gets stuck in local minima and lacks effective exploration.
method Two-phase model with sampling mechanisms and self-attention modules.
result Significantly outperforms previous state-of-the-art in various environments.
Suppose that we are given a time series where consecutive samples are believed to come from a probabilistic source, that the source changes from time to time and that the total number of sources is fixed. Our objective is to estimate the distributions of the sources. A standard approach to this problem is to model the …
Hidden Markov Models (HMMs) are a ubiquitous tool to model time series data, and have been widely used in two main tasks of Automatic Music Transcription (AMT): note segmentation, i.e. identifying the played notes after a multi-pitch estimation, and sequential post-processing, i.e. correcting note segmentation using tr…
The hidden Markov model (HMM) is a widely-used generative model that copes with sequential data, assuming that each observation is conditioned on the state of a hidden Markov chain. In this paper, we derive a novel algorithm to cluster HMMs based on the hierarchical EM (HEM) algorithm. The proposed algorithm i) cluster…
As one of Bayesian analysis tools, Hidden Markov Model (HMM) has been used to in extensive applications. Most HMMs are solved by Baum-Welch algorithm (BWHMM) to predict the model parameters, which is difficult to find global optimal solutions. This paper proposes an optimized Hidden Markov Model with Particle Swarm Opt…
Analysis of pretrained models' effectiveness in downstream tasks.
problem Understanding why pretrained models perform well in NLP tasks.
method Analyzed head and prompt tuning approaches using latent variable models.
result Prompt tuning provides stronger guarantees than head tuning.
We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time spot follows a Gaussian mixture distribution, a fact exploited to softly matc…
This paper addresses the issue of model selection for hidden Markov models (HMMs). We generalize factorized asymptotic Bayesian inference (FAB), which has been recently developed for model selection on independent hidden variables (i.e., mixture models), for time-dependent hidden variables. As with FAB in mixture model…
We consider the smoothing probabilities of hidden Markov model (HMM). We show that under fairly general conditions for HMM, the exponential forgetting still holds, and the smoothing probabilities can be well approximated with the ones of double sided HMM. This makes it possible to use ergodic theorems. As an applicatio…
Behavior cloning can achieve horizon-independent sample complexity in offline imitation learning.
problem Sample complexity in imitation learning increases with problem horizon.
method New analysis of behavior cloning with logarithmic loss.
result Behavior cloning can achieve linear dependence on horizon in offline IL under dense rewards.
Eye Movement analysis with Hidden Markov Models (EMHMM) is a method for modeling eye fixation sequences using hidden Markov models (HMMs). In this report, we run a simulation study to investigate the estimation error for learning HMMs with variational Bayesian inference, with respect to the number of sequences and the …
New method detects anomalies in time series data using HMMs.
problem Detect anomalies in discrete time series data.
method HMM gauge likelihood analysis (HMM GLA) using Baum-Welch algorithm and clustering.
result Successfully detects anomalies in synthetic and real-world syslog data.
AI agent plays CSGO deathmatch with human-like style.
problem Lack of API for CSGO limits data for reinforcement learning.
method Behavioural cloning on large noisy and expert datasets.
result Matches human difficulty level in deathmatch mode.
BCO* improves BCO by concurrently training inverse dynamics and expert policy.
problem Efficiently learn from unlabeled demonstrations without requiring many initial interactions.
method Introduce BCO* that concurrently trains an inverse dynamics model and expert policy.
result BCO* eliminates the need for initial interactions and improves sample complexity.
We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time position follows a Gaussian mixture distribution, a fact exploited to softly …
In this paper, we explore the effectiveness of dynamic analysis techniques for identifying malware, using Hidden Markov Models (HMMs) and Profile Hidden Markov Models (PHMMs), both trained on sequences of API calls. We contrast our results to static analysis using HMMs trained on sequences of opcodes, and show that dyn…
We consider learning parameters of Binomial Hidden Markov Models, which may be used to model DNA methylation data. The standard algorithm for the problem is EM, which is computationally expensive for sequences of the scale of the mammalian genome. Recently developed spectral algorithms can learn parameters of latent va…
Efficiently models tree-like data with coupled branches using HMMs.
problem Modeling sequential data with coupled branches in biological systems.
method Developed a dynamic programming algorithm for tree-based HMMs with coupled branches.
result Efficiently solves likelihood, decoding, and parameter learning problems for tree-based HMMs with coupled branches.
New algorithm for aggregate inference in HMMs with continuous observations.
problem Inference in large populations with indistinguishable individuals and continuous measurements.
method Continuous observation collective forward-backward algorithm extending existing discrete case algorithm.
result Efficacy demonstrated through numerical experiments.
Enhances fraud detection with multiple HMM perspectives.
problem Detecting credit card fraud from sequential transactions.
method Modeling credit card transactions from three perspectives (card-holder, terminal, amount/time) using HMMs and combining likelihoods as features.
result 15% increase in precision-recall AUC compared to state-of-the-art methods.
Scalable hybrid HMM with Gaussian Process for time-series data clustering.
problem Large number of parameters and long sequences in time-series data make HMM-GPSM training difficult.
method Stochastic Variational Inference (SVI) for long sequences and reparameterized random Fourier features (R-RFF) for large data points.
result Significant reduction in training time and improved hidden-state estimation accuracy.
Bayesian HMM for protein alignment state estimation.
problem Estimating the MAP state sequence for a Bayesian HMM.
method Training data with Dirichlet priors, iterative algorithms for MAP path estimation.
result Bayesian setup outperforms frequentist estimation in protein alignment.
Hidden Markov Models (HMM) have been used for several years in many time series analysis or pattern recognitions tasks. HMM are often trained by means of the Baum-Welch algorithm which can be seen as a special variant of an expectation maximization (EM) algorithm. Second-order training techniques such as Variational Ba…