Generalized Model Predictive Path Integral Control as Expectation--Maximization

Jiarui Wang; Mahyar Fazlyab; Sina Sharifi

arxiv: 2606.00317 · v1 · pith:HEKCEW5Onew · submitted 2026-05-29 · 📡 eess.SY · cs.SY· math.OC

Generalized Model Predictive Path Integral Control as Expectation--Maximization

Jiarui Wang , Sina Sharifi , Mahyar Fazlyab This is my paper

Pith reviewed 2026-06-28 21:04 UTC · model grok-4.3

classification 📡 eess.SY cs.SYmath.OC

keywords Model Predictive Path IntegralExpectation-Maximizationstochastic optimal controlconvergence analysisprobabilistic inferenceexponential familiessampling-based controltrajectory optimization

0 comments

The pith

MPPI control arises as a special case of the Expectation-Maximization algorithm on a probabilistic formulation of optimal control.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that the sampling-based MPPI method is exactly one run of the EM algorithm when optimal control is recast as inferring high-reward trajectories from a prior distribution. This equivalence immediately produces a generalized version of MPPI that works with any exponential-family distribution instead of being restricted to Gaussians. The authors then derive local convergence rates expressed through the covariances of the posterior trajectory distribution and the exploration distribution, plus a sufficient-increase guarantee for the log-likelihood when the log-partition function is strongly convex. A reader would care because the unification supplies the first explicit convergence theory for a controller already running on real robots and opens the door to importing other EM techniques into sampling-based control.

Core claim

MPPI can be interpreted as a special case of the EM algorithm applied to a probabilistic inference formulation of optimal control. This perspective leads to a generalized EM-MPPI framework that extends MPPI beyond the commonly used Gaussian parameterization. The convergence behavior of the algorithm is characterized in terms of the covariance of the posterior trajectory distribution and the exploration distribution. For exponential-family distributions, a sufficient increase property of the log-likelihood holds when the log-partition function is strongly convex. Specializing the analysis to Gaussian MPPI yields explicit global and local convergence characterizations.

What carries the argument

The EM algorithm applied to the probabilistic inference formulation of stochastic optimal control, which recovers MPPI when the trajectory distribution is chosen Gaussian.

If this is right

The generalized framework extends MPPI to non-Gaussian exponential-family distributions while retaining its sampling-based character.
Local convergence rate of EM-MPPI is bounded explicitly by the covariances of the posterior and exploration distributions.
Gaussian MPPI receives explicit global and local convergence characterizations as a direct corollary.
For any exponential family whose log-partition function is strongly convex, each EM-MPPI step is guaranteed to increase the log-likelihood.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The covariance-based rate could be used to adaptively tune the exploration covariance on-line to accelerate convergence.
Other sampling-based controllers in robotics might admit similar EM reformulations, allowing convergence analysis to transfer across methods.
Acceleration techniques developed for EM (such as variance reduction or momentum) could be imported directly into the generalized MPPI loop.

Load-bearing premise

The stochastic optimal control problem admits an exact probabilistic inference formulation to which the standard EM algorithm can be applied without approximation error that would invalidate the claimed equivalence or convergence rates.

What would settle it

A control problem and distribution family where running the generalized EM-MPPI iterations produces no increase in the log-likelihood even though the log-partition function satisfies strong convexity.

read the original abstract

Model Predictive Path Integral (MPPI) control is a powerful sampling-based method for solving stochastic optimal control problems and has enabled real-time control in complex robotic systems. Despite its empirical success, its theoretical understanding remains limited. In this work, we show that MPPI can be interpreted as a special case of the Expectation-Maximization (EM) algorithm applied to a probabilistic inference formulation of optimal control. This perspective leads to a generalized EM-MPPI framework that extends MPPI beyond the commonly used Gaussian parameterization. We analyze the convergence behavior of this algorithm and characterize the local convergence rate in terms of the covariance of the posterior trajectory distribution and the exploration distribution. For exponential-family distributions, we establish a sufficient increase property of the log-likelihood when the log-partition function is strongly convex. Specializing the analysis to Gaussian MPPI yields explicit global and local convergence characterizations. The code for the experiments will be available upon acceptance.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper recasts MPPI as a special case of EM on a probabilistic inference formulation of stochastic optimal control, which yields a non-Gaussian generalization plus covariance-based convergence rates.

read the letter

The main point is that MPPI gets derived as EM applied to an exact inference version of the stochastic optimal control problem. This produces a generalized EM-MPPI that works with other distributions and supplies local convergence rates tied to posterior and exploration covariances, plus a sufficient-increase property for exponential families when the log-partition function is strongly convex. Specializing back to the usual Gaussian MPPI then gives explicit global and local rates.

What the paper does well is take an empirically successful sampling controller and supply a clean theoretical framing plus convergence analysis that was not in the earlier MPPI papers. The covariance characterization and the exponential-family result look like concrete additions that could be checked.

The soft spot is the initial mapping itself. The abstract treats the probabilistic inference formulation as exact so that standard EM applies without error, but path-integral methods often involve importance sampling or other steps that can introduce bias or approximation. If any such relaxation is hidden in the derivation, the special-case claim and the subsequent rates would not hold as stated. The paper promises code on acceptance, which should help verify the steps.

This is for people already working on sampling-based stochastic control or EM applications in robotics. A reader who wants theoretical grounding for MPPI-style methods or who follows convergence analysis for iterative controllers would get something usable from it. It deserves a serious referee because the connection is new enough and the claims are specific enough to be tested directly.

Referee Report

3 major / 2 minor

Summary. The paper claims that MPPI control is a special case of the EM algorithm applied to a probabilistic inference formulation of stochastic optimal control. This yields a generalized EM-MPPI framework extending MPPI beyond Gaussian parameterizations, with convergence analysis characterizing local rates via posterior and exploration covariances, a sufficient-increase property for exponential families when the log-partition function is strongly convex, and explicit global/local results when specialized to Gaussian MPPI.

Significance. If the central equivalence is exact (no hidden approximations in the inference mapping), the work supplies a principled theoretical foundation for MPPI, enables non-Gaussian extensions, and delivers concrete convergence characterizations that could guide practical tuning; the stated availability of code would further strengthen reproducibility.

major comments (3)

[Abstract] Abstract (lines on the MPPI-EM interpretation): the claim that MPPI arises as an exact special case of standard EM requires that the stochastic optimal control problem admits an exact (non-approximated) probabilistic inference formulation; any variational bound, biased importance sampling, or inexact evidence computation would invalidate both the special-case statement and the subsequent convergence rates.
[Convergence analysis] Convergence analysis section (characterization of local rate): the stated dependence of the local convergence rate on the covariance of the posterior trajectory distribution and the exploration distribution must be shown to follow directly from the EM fixed-point analysis without additional post-hoc assumptions on the trajectory likelihood or the path-integral approximation.
[Exponential-family section] Exponential-family section (sufficient-increase property): the proof that the log-likelihood exhibits a sufficient increase when the log-partition function is strongly convex needs to confirm that the strong-convexity assumption is preserved under the specific trajectory distribution induced by the control problem, rather than being imposed externally.

minor comments (2)

Clarify notation for the exploration distribution versus the posterior trajectory distribution throughout the derivations to avoid ambiguity in the covariance expressions.
Add explicit comparison to prior control-as-inference literature (e.g., KL-control and variational formulations) to situate the novelty of the MPPI-EM link.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major point below with clarifications on the exactness of the EM equivalence, the direct derivation of convergence rates, and the preservation of strong convexity. Revisions will be made where they strengthen the presentation without altering the core claims.

read point-by-point responses

Referee: [Abstract] Abstract (lines on the MPPI-EM interpretation): the claim that MPPI arises as an exact special case of standard EM requires that the stochastic optimal control problem admits an exact (non-approximated) probabilistic inference formulation; any variational bound, biased importance sampling, or inexact evidence computation would invalidate both the special-case statement and the subsequent convergence rates.

Authors: The probabilistic inference formulation used is exact: the optimal control objective is rewritten as an evidence lower bound that becomes equality under the chosen trajectory distribution and cost encoding, with no variational approximation or biased sampling. MPPI then corresponds precisely to the EM coordinate ascent on this exact objective. We will revise the abstract to explicitly state that the mapping is exact (no hidden approximations) and add a short paragraph in Section 2 confirming the absence of bounds or sampling bias. revision: yes
Referee: [Convergence analysis] Convergence analysis section (characterization of local rate): the stated dependence of the local convergence rate on the covariance of the posterior trajectory distribution and the exploration distribution must be shown to follow directly from the EM fixed-point analysis without additional post-hoc assumptions on the trajectory likelihood or the path-integral approximation.

Authors: The local rate expression is obtained by linearizing the EM operator around the fixed point and substituting the explicit forms of the posterior covariance (from the E-step) and exploration covariance (from the sampling distribution in the M-step). This follows directly from the standard EM convergence analysis for exponential families without further assumptions on the likelihood beyond those already used to establish the Q-function. We will expand the derivation in the revised Section 4 to make each algebraic step explicit. revision: yes
Referee: [Exponential-family section] Exponential-family section (sufficient-increase property): the proof that the log-likelihood exhibits a sufficient increase when the log-partition function is strongly convex needs to confirm that the strong-convexity assumption is preserved under the specific trajectory distribution induced by the control problem, rather than being imposed externally.

Authors: Strong convexity is a property of the chosen exponential-family parameterization and is inherited by any distribution in that family, including the trajectory distribution induced by the dynamics and control. Because the base measure and sufficient statistics are fixed by the problem formulation, the Hessian of the log-partition remains positive definite under the induced measure. We will add a short lemma in the exponential-family section verifying that the control-induced distribution stays within the family for which strong convexity holds. revision: yes

Circularity Check

0 steps flagged

No circularity: MPPI-EM link is an interpretive derivation with independent convergence analysis

full rationale

The paper frames MPPI as a special case of EM on a probabilistic inference formulation of stochastic optimal control, then derives a generalized framework and convergence rates (local via posterior/exploration covariances; sufficient-increase for strongly convex log-partition in exponential families) from standard EM properties. No equations reduce a claimed result to its own fitted inputs by construction, no load-bearing self-citations are invoked for uniqueness or ansatzes, and the mapping is presented as a derivation rather than a redefinition. The analysis remains self-contained against external EM theory without requiring the target result as an assumption.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that optimal control admits an exact probabilistic inference formulation to which EM applies directly; no free parameters or invented entities are mentioned in the abstract.

axioms (1)

domain assumption The stochastic optimal control problem can be exactly recast as a probabilistic inference problem to which the EM algorithm applies without residual approximation error.
This premise is required for the claimed equivalence and for the subsequent convergence analysis to hold.

pith-pipeline@v0.9.1-grok · 5695 in / 1207 out tokens · 22415 ms · 2026-06-28T21:04:18.960549+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

24 extracted references · 6 canonical work pages · 3 internal anchors

[1]

Aggressive driving with model pre- dictive path integral control

Grady Williams et al. “Aggressive driving with model pre- dictive path integral control”. In:2016 IEEE international conference on robotics and automation (ICRA). IEEE. 2016, pp. 1433–1440

2016
[2]

Information theoretic MPC for model- based reinforcement learning

Grady Williams et al. “Information theoretic MPC for model- based reinforcement learning”. In:2017 IEEE international conference on robotics and automation (ICRA). IEEE. 2017, pp. 1714–1721

2017
[3]

Mujoco: A physics engine for model-based control

Emanuel Todorov, Tom Erez, and Yuval Tassa. “Mujoco: A physics engine for model-based control”. In:2012 IEEE/RSJ international conference on intelligent robots and systems. IEEE. 2012, pp. 5026–5033

2012
[4]

Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning

Viktor Makoviychuk et al. “Isaac gym: High performance gpu-based physics simulation for robot learning”. In:arXiv preprint arXiv:2108.10470(2021)

work page internal anchor Pith review Pith/arXiv arXiv 2021
[5]

Real-time whole-body control of legged robots with model-predictive path integral control

Juan Alvarez-Padilla et al. “Real-time whole-body control of legged robots with model-predictive path integral control”. In:2025 IEEE International Conference on Robotics and Automation (ICRA). IEEE. 2025, pp. 14721–14727

2025
[6]

Pa-mppi: Perception-aware model predictive path integral control for quadrotor navigation in unknown environments

Yifan Zhai, Rudolf Reiter, and Davide Scaramuzza. “Pa-mppi: Perception-aware model predictive path integral control for quadrotor navigation in unknown environments”. In:arXiv preprint arXiv:2509.14978(2025)

work page arXiv 2025
[7]

Residual-mppi: Online policy customization for continuous control

Pengcheng Wang et al. “Residual-mppi: Online policy customization for continuous control”. In:arXiv preprint arXiv:2407.00898(2024)

work page arXiv 2024
[8]

Model Predictive Control via Probabilistic Inference: A Tutorial and Survey

Kohei Honda. “Model Predictive Control via Probabilistic Inference: A Tutorial”. In:arXiv preprint arXiv:2511.08019 (2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[9]

CoVO-MPC: Theoretical analysis of sampling- based MPC and optimal covariance design

Zeji Yi et al. “CoVO-MPC: Theoretical analysis of sampling- based MPC and optimal covariance design”. In:6th Annual Learning for Dynamics & Control Conference. PMLR. 2024, pp. 1122–1135

2024
[10]

Optimality and suboptimality of MPPI control in stochastic and deterministic settings

Hannes Homburger et al. “Optimality and suboptimality of MPPI control in stochastic and deterministic settings”. In: IEEE Control Systems Letters(2025)

2025
[11]

Op- timal control as a graphical model inference problem

Hilbert J Kappen, Vicenc ¸ G ´omez, and Manfred Opper. “Op- timal control as a graphical model inference problem”. In: Machine learning87.2 (2012), pp. 159–182

2012
[12]

Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review

Sergey Levine. “Reinforcement learning and control as prob- abilistic inference: Tutorial and review”. In:arXiv preprint arXiv:1805.00909(2018)

work page internal anchor Pith review Pith/arXiv arXiv 2018
[13]

Variational infer- ence mpc for bayesian model-based reinforcement learning

Masashi Okada and Tadahiro Taniguchi. “Variational infer- ence mpc for bayesian model-based reinforcement learning”. In:Conference on robot learning. PMLR. 2020, pp. 258–272

2020
[14]

The cross-entropy method for opti- mization

Zdravko I Botev et al. “The cross-entropy method for opti- mization”. In:Handbook of statistics. V ol. 31. Elsevier, 2013, pp. 35–59

2013
[15]

Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA- ES)

Nikolaus Hansen, Sibylle D M ¨uller, and Petros Koumout- sakos. “Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA- ES)”. In:Evolutionary computation11.1 (2003), pp. 1–18

2003
[16]

Variational inference MPC using Tsallis divergence

Ziyi Wang et al. “Variational inference MPC using Tsallis divergence”. In:arXiv preprint arXiv:2104.00241(2021)

work page arXiv 2021
[17]

Maximum likelihood from incomplete data via the EM algorithm

Arthur P Dempster, Nan M Laird, and Donald B Rubin. “Maximum likelihood from incomplete data via the EM algorithm”. In:Journal of the royal statistical society: series B (methodological)39.1 (1977), pp. 1–22

1977
[18]

John Wiley & Sons, 2008

Geoffrey J McLachlan and Thriyambakam Krishnan.The EM algorithm and extensions. John Wiley & Sons, 2008

2008
[19]

MIT press, 2009

Daphne Koller and Nir Friedman.Probabilistic graphical models: principles and techniques. MIT press, 2009

2009
[20]

Using expectation- maximization for reinforcement learning

Peter Dayan and Geoffrey E Hinton. “Using expectation- maximization for reinforcement learning”. In:Neural Com- putation9.2 (1997), pp. 271–278

1997
[21]

Expectation-Maximization methods for solving (PO) MDPs and optimal control problems

Marc Toussaint, Amos Storkey, and Stefan Harmeling. “Expectation-Maximization methods for solving (PO) MDPs and optimal control problems”. In:Bayesian Time Series Models(2011), pp. 388–413

2011
[22]

Stochastic optimal con- trol for multivariable dynamical systems using expectation maximization

Prakash Mallick and Zhiyong Chen. “Stochastic optimal con- trol for multivariable dynamical systems using expectation maximization”. In:IEEE Transactions on Neural Networks and Learning Systems34.9 (2022), pp. 5268–5282

2022
[23]

On the convergence properties of the EM algorithm

CF Jeff Wu. “On the convergence properties of the EM algorithm”. In:The Annals of statistics(1983), pp. 95–103

1983
[24]

SIAM, 2000

James M Ortega and Werner C Rheinboldt.Iterative solution of nonlinear equations in several variables. SIAM, 2000. IX. APPENDIX APPENDIX A. Proof of Theorem 1 Let ˆℓ(θ) := Z p(u;θ) exp(−J(u)/τ)du. We show that ˆℓ(θ)→0as∥θ∥ → ∞. FixM >0and decompose ˆℓ(θ)= Z ∥u∥≤M p(u;θ)e −J(u)/τ du+ Z ∥u∥>M p(u;θ)e −J(u)/τ du. Let J(M) := inf ∥u∥≥M J(u). By Assumption 1,J...

2000

[1] [1]

Aggressive driving with model pre- dictive path integral control

Grady Williams et al. “Aggressive driving with model pre- dictive path integral control”. In:2016 IEEE international conference on robotics and automation (ICRA). IEEE. 2016, pp. 1433–1440

2016

[2] [2]

Information theoretic MPC for model- based reinforcement learning

Grady Williams et al. “Information theoretic MPC for model- based reinforcement learning”. In:2017 IEEE international conference on robotics and automation (ICRA). IEEE. 2017, pp. 1714–1721

2017

[3] [3]

Mujoco: A physics engine for model-based control

Emanuel Todorov, Tom Erez, and Yuval Tassa. “Mujoco: A physics engine for model-based control”. In:2012 IEEE/RSJ international conference on intelligent robots and systems. IEEE. 2012, pp. 5026–5033

2012

[4] [4]

Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning

Viktor Makoviychuk et al. “Isaac gym: High performance gpu-based physics simulation for robot learning”. In:arXiv preprint arXiv:2108.10470(2021)

work page internal anchor Pith review Pith/arXiv arXiv 2021

[5] [5]

Real-time whole-body control of legged robots with model-predictive path integral control

Juan Alvarez-Padilla et al. “Real-time whole-body control of legged robots with model-predictive path integral control”. In:2025 IEEE International Conference on Robotics and Automation (ICRA). IEEE. 2025, pp. 14721–14727

2025

[6] [6]

Pa-mppi: Perception-aware model predictive path integral control for quadrotor navigation in unknown environments

Yifan Zhai, Rudolf Reiter, and Davide Scaramuzza. “Pa-mppi: Perception-aware model predictive path integral control for quadrotor navigation in unknown environments”. In:arXiv preprint arXiv:2509.14978(2025)

work page arXiv 2025

[7] [7]

Residual-mppi: Online policy customization for continuous control

Pengcheng Wang et al. “Residual-mppi: Online policy customization for continuous control”. In:arXiv preprint arXiv:2407.00898(2024)

work page arXiv 2024

[8] [8]

Model Predictive Control via Probabilistic Inference: A Tutorial and Survey

Kohei Honda. “Model Predictive Control via Probabilistic Inference: A Tutorial”. In:arXiv preprint arXiv:2511.08019 (2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025

[9] [9]

CoVO-MPC: Theoretical analysis of sampling- based MPC and optimal covariance design

Zeji Yi et al. “CoVO-MPC: Theoretical analysis of sampling- based MPC and optimal covariance design”. In:6th Annual Learning for Dynamics & Control Conference. PMLR. 2024, pp. 1122–1135

2024

[10] [10]

Optimality and suboptimality of MPPI control in stochastic and deterministic settings

Hannes Homburger et al. “Optimality and suboptimality of MPPI control in stochastic and deterministic settings”. In: IEEE Control Systems Letters(2025)

2025

[11] [11]

Op- timal control as a graphical model inference problem

Hilbert J Kappen, Vicenc ¸ G ´omez, and Manfred Opper. “Op- timal control as a graphical model inference problem”. In: Machine learning87.2 (2012), pp. 159–182

2012

[12] [12]

Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review

Sergey Levine. “Reinforcement learning and control as prob- abilistic inference: Tutorial and review”. In:arXiv preprint arXiv:1805.00909(2018)

work page internal anchor Pith review Pith/arXiv arXiv 2018

[13] [13]

Variational infer- ence mpc for bayesian model-based reinforcement learning

Masashi Okada and Tadahiro Taniguchi. “Variational infer- ence mpc for bayesian model-based reinforcement learning”. In:Conference on robot learning. PMLR. 2020, pp. 258–272

2020

[14] [14]

The cross-entropy method for opti- mization

Zdravko I Botev et al. “The cross-entropy method for opti- mization”. In:Handbook of statistics. V ol. 31. Elsevier, 2013, pp. 35–59

2013

[15] [15]

Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA- ES)

Nikolaus Hansen, Sibylle D M ¨uller, and Petros Koumout- sakos. “Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA- ES)”. In:Evolutionary computation11.1 (2003), pp. 1–18

2003

[16] [16]

Variational inference MPC using Tsallis divergence

Ziyi Wang et al. “Variational inference MPC using Tsallis divergence”. In:arXiv preprint arXiv:2104.00241(2021)

work page arXiv 2021

[17] [17]

Maximum likelihood from incomplete data via the EM algorithm

Arthur P Dempster, Nan M Laird, and Donald B Rubin. “Maximum likelihood from incomplete data via the EM algorithm”. In:Journal of the royal statistical society: series B (methodological)39.1 (1977), pp. 1–22

1977

[18] [18]

John Wiley & Sons, 2008

Geoffrey J McLachlan and Thriyambakam Krishnan.The EM algorithm and extensions. John Wiley & Sons, 2008

2008

[19] [19]

MIT press, 2009

Daphne Koller and Nir Friedman.Probabilistic graphical models: principles and techniques. MIT press, 2009

2009

[20] [20]

Using expectation- maximization for reinforcement learning

Peter Dayan and Geoffrey E Hinton. “Using expectation- maximization for reinforcement learning”. In:Neural Com- putation9.2 (1997), pp. 271–278

1997

[21] [21]

Expectation-Maximization methods for solving (PO) MDPs and optimal control problems

Marc Toussaint, Amos Storkey, and Stefan Harmeling. “Expectation-Maximization methods for solving (PO) MDPs and optimal control problems”. In:Bayesian Time Series Models(2011), pp. 388–413

2011

[22] [22]

Stochastic optimal con- trol for multivariable dynamical systems using expectation maximization

Prakash Mallick and Zhiyong Chen. “Stochastic optimal con- trol for multivariable dynamical systems using expectation maximization”. In:IEEE Transactions on Neural Networks and Learning Systems34.9 (2022), pp. 5268–5282

2022

[23] [23]

On the convergence properties of the EM algorithm

CF Jeff Wu. “On the convergence properties of the EM algorithm”. In:The Annals of statistics(1983), pp. 95–103

1983

[24] [24]

SIAM, 2000

James M Ortega and Werner C Rheinboldt.Iterative solution of nonlinear equations in several variables. SIAM, 2000. IX. APPENDIX APPENDIX A. Proof of Theorem 1 Let ˆℓ(θ) := Z p(u;θ) exp(−J(u)/τ)du. We show that ˆℓ(θ)→0as∥θ∥ → ∞. FixM >0and decompose ˆℓ(θ)= Z ∥u∥≤M p(u;θ)e −J(u)/τ du+ Z ∥u∥>M p(u;θ)e −J(u)/τ du. Let J(M) := inf ∥u∥≥M J(u). By Assumption 1,J...

2000