tfp.optim.lbfgs_minimize fails where scipy.optimize and torch.optim.LBFGS succeed for poisson optimization

For this minimal example of fitting a 1-parameter poissonian likelihood Pois(10|par) where you would expect the best-fit value to be 10.0 tfp seems to fail:

tf.reset_default_graph()
sess = tf.Session()
def func_tf(pars):
    nll = -tfp.distributions.Poisson(pars).log_prob(10.)
    grad = tf.identity(tf.gradients(nll,pars))[0]
    return nll[0],grad

result = sess.run(tfp.optimizer.lbfgs_minimize(func_tf,tf.convert_to_tensor([1.6])))
'converged: {}, failed: {}, position: {}'.format(result.converged,result.failed,result.position)

gives:

'converged: False, failed: True, position: [11.124551]'

the optimization fails.

Interestingly it seems to be quite sensitive to the initial position. If I change the initial position to 10.5 the minimization succeeds:

result = sess.run(tfp.optimizer.lbfgs_minimize(func_tf,tf.convert_to_tensor([10.5])))
'converged: {}, failed: {}, position: {}'.format(result.converged,result.failed,result.position)

'converged: True, failed: False, position: [10.]'

As a cross-check I tried using the LBFGS optimizers in scipy.optimize and PyTorch to see if this is an issue, and in those cases the initial position 1.6 seems ok

Note: in scipy I had to cast to double precision due to: https://github.com/scipy/scipy/issues/5832

I'm attaching a screentshot of the full notebook, which is available here: https://gist.github.com/lukasheinrich/327ab8bf1b96e9af3e483a4b26d435ea

cc @matthewfeickert @kratsg

Start by running the minimal notebook example through tfp.optimizer.lbfgs_minimize with initial positions 1.6 and 10.5, then compare the reported convergence, failure, and position. Trace the optimizer's behavior for the one-parameter Poisson likelihood and verify that the 1.6 case converges to the expected position of 10.0 without breaking the successful case.