def main(): epochs = 10 batches = 4096 z_k = 1024 iters = 5 outputpath = "output/skipgram_flat-l1" cooccurrence = np.load('output/cooccurrence.npy').astype(np.float32) weights = [1e-4, 1e-5, 1e-6, 1e-7, 5e-8, 1e-8, 5e-9, 1e-9] regularizers = [l1(w) for w in weights] labels = ["l1-{:.01e}".format(w) for w in weights] train_flat_regularizer_battery(outputpath=outputpath, cooccurrence=cooccurrence, epochs=epochs, batches=batches, iters=iters, z_k=z_k, labels=labels, regularizers=regularizers, is_weight_regularizer=True, kwdata={'weights': np.array(weights)})
def main(): epochs = 10 batches = 4096 z_k = 256 iters = 1 outputpath = "output/skipgram_256-el" cooccurrence = np.load('output/cooccurrence.npy').astype(np.float32) weights = [1e-7, 1e-8, 1e-9, 1e-10, 1e-11, 1e-12, 1e-13] regularizers = [ExclusiveLasso(w) for w in weights] labels = ["el-{:.01e}".format(w) for w in weights] train_flat_regularizer_battery(outputpath=outputpath, cooccurrence=cooccurrence, epochs=epochs, batches=batches, iters=iters, z_k=z_k, labels=labels, regularizers=regularizers, is_weight_regularizer=True, kwdata={'weights': np.array(weights)})
def main(): epochs = 10 batches = 4096 z_k = 1024 iters = 3 outputpath = "output/skipgram_1024_h" cooccurrence = np.load('output/cooccurrence.npy').astype(np.float32) weights = [1e-1, 1e-2, 1e-3, 1e-4, 1e-5, 1e-6, 1e-7] regularizers = [EntropyRegularizer(w) for w in weights] labels = ["h-{:.01e}".format(w) for w in weights] train_flat_regularizer_battery(outputpath=outputpath, cooccurrence=cooccurrence, epochs=epochs, batches=batches, iters=iters, z_k=z_k, labels=labels, regularizers=regularizers, is_weight_regularizer=False, kwdata={'weights': np.array(weights)})