def test_f1backtrack(gf):
projSplit = ps.ProjSplitFit()
m = 10
d = 20
if getNewOptVals and (gf == 1.0):
A = np.random.normal(0, 1, [m, d])
y = np.random.normal(0, 1, m)
cache['Af1bt'] = A
cache['yf1bt'] = y
else:
A = cache['Af1bt']
y = cache['yf1bt']
processor = lp.Forward1Backtrack(growFactor=gf, growFreq=10)
projSplit.setDualScaling(1e-1)
projSplit.addData(A, y, 2, processor, intercept=True, normalize=True)
vec = projSplit.getScaling()
assert len(vec) == d
projSplit.run(maxIterations=None,
keepHistory=True,
primalTol=1e-3,
dualTol=1e-3,
nblocks=5)
ps_val = projSplit.getObjective()
if getNewOptVals and (gf == 1.0):
AwithIntercept = np.zeros((m, d + 1))
AwithIntercept[:, 0] = np.ones(m)
AwithIntercept[:, 1:(d + 1)] = A
result = np.linalg.lstsq(AwithIntercept, y, rcond=None)
xhat = result[0]
LSval = 0.5 * np.linalg.norm(AwithIntercept.dot(xhat) - y, 2)**2 / m
cache['optf1bt'] = LSval
else:
LSval = cache['optf1bt']
assert ps_val - LSval < 1e-2
H = np.random.normal(0,1,[d2,p])
try:
projSplit.addData(A,y,2,processor,normalize=False,intercept=False,
linearOp = aslinearoperator(H))
notExcept = True
except:
notExcept = False
assert notExcept == False
f2fix = lp.Forward2Fixed()
back2exact = lp.BackwardExact()
backCG = lp.BackwardCG()
f1bt = lp.Forward1Backtrack()
backLB = lp.BackwardLBFGS()
TryAll = []
testNumber = 0
for i in [False,True]:
for j in [False,True]:
for k in [False,True]:
for l in [False,True]:
for p in [backLB,f2fix,back2exact,f1bt,backCG]:
TryAll.append((i,j,k,l,p,testNumber))
testNumber += 1
@pytest.mark.parametrize("norm,inter,addL1,add2L1,processor,testNumber",TryAll)
def test_linear_op_data_term(norm,inter,addL1,add2L1,processor,testNumber):
psObj = ps.ProjSplitFit(gamma)
proc = lp.Forward2Backtrack()
psObj.addData(X,y,loss2use,linearOp=H,normalize=False,process=proc,
embed=regularizers.L1(scaling=(1-mu)*lam))
(nbeta,ngamma) = H.shape
shape = (ngamma-1,ngamma)
G_for_ps = sl.LinearOperator(shape,matvec=lambda x: x[:-1],rmatvec = lambda x : np.concatenate((x,np.array([0]))))
psObj.addRegularizer(regularizers.L1(scaling = mu*lam,step=tuned),linearOp=G_for_ps)
psObj.run(nblocks=10,maxIterations=maxIter,verbose=False,keepHistory=False,
primalTol=0.0,dualTol=0.0,blockActivation="greedy")
results[(i,'ps2fembed_g')] = psObj.getObjective()
if False:
psObj = ps.ProjSplitFit(gamma)
psObj.addData(X,y,loss2use,linearOp=H,normalize=False,process=lp.Forward1Backtrack(),
embed=regularizers.L1(scaling=(1-mu)*lam))
(nbeta,ngamma) = H.shape
shape = (ngamma-1,ngamma)
G_for_ps = sl.LinearOperator(shape,matvec=lambda x: x[:-1],rmatvec = lambda x : np.concatenate((x,np.array([0]))))
psObj.addRegularizer(regularizers.L1(scaling = mu*lam),linearOp=G_for_ps)
psObj.run(nblocks=1,maxIterations=maxIter,verbose=False,keepHistory=False,
primalTol=0.0,dualTol=0.0)
results[(i,'ps1fembed')] = psObj.getObjective()
if False:
psObj = ps.ProjSplitFit(gamma)
psObj.addData(X,y,loss2use,linearOp=H,normalize=False,process=lp.BackwardLBFGS())
psObj.addRegularizer(regularizers.L1(scaling=(1-mu)*lam),linearOp=H)
(nbeta,ngamma) = H.shape
shape = (ngamma-1,ngamma)
t_ps2f = psObj.getHistory()[1]
t1 = time.time()
print(f"ps2f total running time {t1-t0}")
if run1f:
print("1f")
gamma1f = gamma1fs[i]
t0 = time.time()
psObj = ps.ProjSplitFit(gamma1f)
if embed:
psObj.addData(X,
y,
loss2use,
linearOp=H,
normalize=False,
process=lp.Forward1Backtrack(),
embed=regularizers.L1(scaling=(1 - mu) * lam))
else:
psObj.addData(X,
y,
loss2use,
linearOp=H,
normalize=False,
process=lp.Forward1Backtrack())
psObj.addRegularizer(regularizers.L1(scaling=(1 - mu) * lam),
linearOp=H)
(nbeta, ngamma) = H.shape
shape = (ngamma - 1, ngamma)
G_for_ps = sl.LinearOperator(shape,
matvec=lambda x: x[:-1],