R: 1D convolution layer (e.g. temporal convolution) with Flipout

layer_conv_1d_flipout {tfprobability}

R Documentation

1D convolution layer (e.g. temporal convolution) with Flipout

Description

This layer creates a convolution kernel that is convolved (actually cross-correlated) with the layer input to produce a tensor of outputs. It may also include a bias addition and activation function on the outputs. It assumes the kernel and/or bias are drawn from distributions.

Usage

layer_conv_1d_flipout(
  object,
  filters,
  kernel_size,
  strides = 1,
  padding = "valid",
  data_format = "channels_last",
  dilation_rate = 1,
  activation = NULL,
  activity_regularizer = NULL,
  trainable = TRUE,
  kernel_posterior_fn = tfp$layers$util$default_mean_field_normal_fn(),
  kernel_posterior_tensor_fn = function(d) d %>% tfd_sample(),
  kernel_prior_fn = tfp$layers$util$default_multivariate_normal_fn,
  kernel_divergence_fn = function(q, p, ignore) tfd_kl_divergence(q, p),
  bias_posterior_fn = tfp$layers$util$default_mean_field_normal_fn(is_singular = TRUE),
  bias_posterior_tensor_fn = function(d) d %>% tfd_sample(),
  bias_prior_fn = NULL,
  bias_divergence_fn = function(q, p, ignore) tfd_kl_divergence(q, p),
  ...
)

Arguments

`object`	What to compose the new `Layer` instance with. Typically a Sequential model or a Tensor (e.g., as returned by `layer_input()`). The return value depends on `object`. If `object` is: missing or `NULL`, the `Layer` instance is returned. a `Sequential` model, the model with an additional layer is returned. a Tensor, the output tensor from `layer_instance(object)` is returned.
`filters`	Integer, the dimensionality of the output space (i.e. the number of filters in the convolution).
`kernel_size`	An integer or list of a single integer, specifying the length of the 1D convolution window.
`strides`	An integer or list of a single integer, specifying the stride length of the convolution. Specifying any stride value != 1 is incompatible with specifying any `dilation_rate` value != 1.
`padding`	One of `"valid"` or `"same"` (case-insensitive).
`data_format`	A string, one of `channels_last` (default) or `channels_first`. The ordering of the dimensions in the inputs. `channels_last` corresponds to inputs with shape `⁠(batch, length, channels)⁠` while `channels_first` corresponds to inputs with shape `⁠(batch, channels, length)⁠`.
`dilation_rate`	An integer or tuple/list of a single integer, specifying the dilation rate to use for dilated convolution. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any `strides` value != 1.
`activation`	Activation function. Set it to None to maintain a linear activation.
`activity_regularizer`	Regularizer function for the output.
`trainable`	Whether the layer weights will be updated during training.
`kernel_posterior_fn`	Function which creates `tfd$Distribution` instance representing the surrogate posterior of the `kernel` parameter. Default value: `default_mean_field_normal_fn()`.
`kernel_posterior_tensor_fn`	Function which takes a `tfd$Distribution` instance and returns a representative value. Default value: `function(d) d %>% tfd_sample()`.
`kernel_prior_fn`	Function which creates `tfd$Distribution` instance. See `default_mean_field_normal_fn` docstring for required parameter signature. Default value: `tfd_normal(loc = 0, scale = 1)`.
`kernel_divergence_fn`	Function which takes the surrogate posterior distribution, prior distribution and random variate sample(s) from the surrogate posterior and computes or approximates the KL divergence. The distributions are `tfd$Distribution`-like instances and the sample is a `Tensor`.
`bias_posterior_fn`	Function which creates a `tfd$Distribution` instance representing the surrogate posterior of the `bias` parameter. Default value: `default_mean_field_normal_fn(is_singular = TRUE)` (which creates an instance of `tfd_deterministic`).
`bias_posterior_tensor_fn`	Function which takes a `tfd$Distribution` instance and returns a representative value. Default value: `function(d) d %>% tfd_sample()`.
`bias_prior_fn`	Function which creates `tfd` instance. See `default_mean_field_normal_fn` docstring for required parameter signature. Default value: `NULL` (no prior, no variational inference)
`bias_divergence_fn`	Function which takes the surrogate posterior distribution, prior distribution and random variate sample(s) from the surrogate posterior and computes or approximates the KL divergence. The distributions are `tfd$Distribution`-like instances and the sample is a `Tensor`.
`...`	Additional keyword arguments passed to the `keras::layer_dense` constructed by this layer.

Details

This layer implements the Bayesian variational inference analogue to a dense layer by assuming the kernel and/or the bias are drawn from distributions.

By default, the layer implements a stochastic forward pass via sampling from the kernel and bias posteriors,

outputs = f(inputs; kernel, bias), kernel, bias ~ posterior

where f denotes the layer's calculation. It uses the Flipout estimator (Wen et al., 2018), which performs a Monte Carlo approximation of the distribution integrating over the kernel and bias. Flipout uses roughly twice as many floating point operations as the reparameterization estimator but has the advantage of significantly lower variance.

The arguments permit separate specification of the surrogate posterior (q(W|x)), prior (p(W)), and divergence for both the kernel and bias distributions.

Upon being built, this layer adds losses (accessible via the losses property) representing the divergences of kernel and/or bias surrogate posteriors and their respective priors. When doing minibatch stochastic optimization, make sure to scale this loss such that it is applied just once per epoch (e.g. if kl is the sum of losses for each element of the batch, you should pass kl / num_examples_per_epoch to your optimizer). You can access the kernel and/or bias posterior and prior distributions after the layer is built via the kernel_posterior, kernel_prior, bias_posterior and bias_prior properties.

Value

a Keras layer

References

Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, and Roger Grosse. Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches. In International Conference on Learning Representations, 2018.